Search Results for author:
Found 169 papers, 85 papers with code
Hebrew Psychological Lexicons
We introduce a large set of Hebrew lexicons pertaining to psychological aspects.
It’s not Greek to mBERT: Inducing Word-Level Translations from Multilingual BERT
Recent works have demonstrated that multilingual BERT (mBERT) learns rich cross-lingual representations, that allow for transfer across languages.
LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements
In particular, while some models prove virtually unaffected by knowledge conflicts in affirmative and negative contexts, when faced with more semantically involved modal and conditional environments, they often fail to separate the text from their internal knowledge.
Leveraging Collection-Wide Similarities for Unsupervised Document Structure Extraction
Document collections of various domains, e. g., legal, medical, or financial, often share some underlying collection-wide structure, which captures information that can aid both human users and structure-aware models.
Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models
This paper explores the impact of extending input lengths on the capabilities of Large Language Models (LLMs).
What Changed? Converting Representational Interventions to Natural Language
Interventions targeting the representation space of language models (LMs) have emerged as effective means to influence model behavior.
Guiding LLM to Fool Itself: Automatically Manipulating Machine Reading Comprehension Shortcut Triggers
Using GPT4 as the editor, we find it can successfully edit trigger shortcut in samples that fool LLMs.
NERetrieve: Dataset for Next Generation Named Entity Recognition and Retrieval
The third, and most challenging, is the move from the recognition setup to a novel retrieval setup, where the query is a zero-shot entity type, and the expected result is all the sentences from a large, pre-indexed corpus that contain entities of these types, and their corresponding spans.
Linguistically Motivated Sign Language Segmentation
We find that introducing BIO tagging is necessary to model sign boundaries.
Hierarchy Builder: Organizing Textual Spans into a Hierarchy to Facilitate Navigation
Information extraction systems often produce hundreds to thousands of strings on a specific topic.
Unsupervised Mapping of Arguments of Deverbal Nouns to Their Corresponding Verbal Labels
Deverbal nouns are nominal forms of verbs commonly used in written English texts to describe events or actions, as well as their arguments.
Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment
This reflects an impaired mapping between linguistic binding of entities and modifiers in the prompt and visual binding of the corresponding elements in the generated image.
An Open-Source Gloss-Based Baseline for Spoken to Signed Language Translation
Sign language translation systems are complex and require many components.
Conjunct Resolution in the Face of Verbal Omissions
In this work we propose a conjunct resolution task that operates directly on the text and makes use of a split-and-rephrase paradigm in order to recover the missing elements in the coordination structure.
Simple Linguistic Inferences of Large Language Models (LLMs): Blind Spots and Blinds
We evaluate LLMs' language understanding capacities on simple inference tasks that most humans find trivial.
Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models
The escalating debate on AI's capabilities warrants developing reliable metrics to assess machine "intelligence".
Retrieving Texts based on Abstract Descriptions
While instruction-tuned Large Language Models (LLMs) excel at extracting information from text, they are not suitable for locating texts conforming to a given description in a large document collection (semantic retrieval).
Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks
Data contamination has become prevalent and challenging with the rise of models pretrained on large automatically-crawled corpora.
Neighboring Words Affect Human Interpretation of Saliency Explanations
Word-level saliency explanations ("heat maps over words") are often used to communicate feature-attribution in text-based models.
Conformal Nucleus Sampling
Language models generate text based on successively sampling the next word.
Training Large Scale Polynomial CNNs for E2E Inference over Homomorphic Encryption
Training large-scale CNNs that during inference can be run under Homomorphic Encryption (HE) is challenging due to the need to use only polynomial operations.
Two Kinds of Recall
I demonstrate through experiments that while neural methods are indeed significantly better at d-recall, it is sometimes the case that pattern-based methods are still substantially better at e-recall.
At Your Fingertips: Extracting Piano Fingering Instructions from Videos
Piano fingering -- knowing which finger to use to play each note in a musical piece, is a hard and important skill to master when learning to play the piano.
Lexical Generalization Improves with Larger Models and Longer Training
While fine-tuned language models perform well on many tasks, they were also shown to rely on superficial surface features such as lexical overlap.
DALLE-2 is Seeing Double: Flaws in Word-to-Concept Mapping in Text2Image Models
We study the way DALLE-2 maps symbols (words) in the prompt to their references (entities or properties of entities in the generated image).
Log-linear Guardedness and its Implications
Methods for erasing human-interpretable concepts from neural representations that assume linearity have been found to be tractable and useful.
CIKQA: Learning Commonsense Inference with a Unified Knowledge-in-the-loop QA Paradigm
We first align commonsense tasks with relevant knowledge from commonsense knowledge bases and ask humans to annotate whether the knowledge is enough or not.
Understanding Transformer Memorization Recall Through Idioms
In this work, we offer the first methodological framework for probing and characterizing recall of memorized sequences in transformer LMs.
F-coref: Fast, Accurate and Easy to Use Coreference Resolution
We introduce fastcoref, a python package for fast, accurate, and easy-to-use English coreference resolution.
Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions
Our causal framework and our results demonstrate the importance of studying datasets and the benefits of causality for understanding NLP models.
Rivendell: Project-Based Academic Search Engine
We posit that in searching for research papers, a combination of a life-time search engine with an explicitly-provided context (project) provides a solution to the concept drift problem.
LingMess: Linguistically Informed Multi Expert Scorers for Coreference Resolution
While coreference resolution typically involves various linguistic challenges, recent models are based on a single pairwise scorer for all types of pairs.
Ranked #4 on
Coreference Resolution
on OntoNotes
A Dataset for N-ary Relation Extraction of Drug Combinations
Furthermore, the relations in this dataset predominantly require language understanding beyond the sentence level, adding to the challenge of this task.
LM-Debugger: An Interactive Tool for Inspection and Intervention in Transformer-Based Language Models
The opaque nature and unexplained behavior of transformer-based language models (LMs) have spurred a wide interest in interpreting their predictions.
Analyzing Gender Representation in Multilingual Models
Multilingual language models were shown to allow for nontrivial transfer across scripts and languages.
Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space
Transformer-based language models (LMs) are at the core of modern NLP, but their internal prediction construction process is opaque and largely not understood.
Linear Adversarial Concept Erasure
Modern neural models trained on textual data rely on pre-trained representations that emerge without direct supervision.
Kernelized Concept Erasure
One prominent approach for the identification of concepts in neural representations is searching for a linear subspace whose erasure prevents the prediction of the concept from the representations.
Diagnosing AI Explanation Methods with Folk Concepts of Behavior
We posit that folk concepts of behavior provide us with a "language" that humans understand behavior with.
Human Interpretation of Saliency-based Explanation Over Text
In this work, we focus on this question through a study of saliency-based explanations over textual data.
CommonsenseQA 2.0: Exposing the Limits of AI through Gamification
Constructing benchmarks that test the abilities of modern natural language understanding models is difficult - pre-trained language models exploit artifacts in benchmarks to achieve human parity, but still fail on adversarial examples and make errors that demonstrate a lack of common sense.
Simple, Interpretable and Stable Method for Detecting Words with Usage Change across Corpora
The problem of comparing two bodies of text and searching for words that differ in their usage between them arises often in digital humanities and computational social science.
Large Scale Substitution-based Word Sense Induction
We present a word-sense induction method based on pre-trained masked language models (MLMs), which can cheaply scale to large vocabularies and large corpora.
Text-based NP Enrichment
Understanding the relations between entities denoted by NPs in a text is a critical part of human-like natural language understanding.
Asking It All: Generating Contextualized Questions for any Semantic Role
We develop a two-stage model for this task, which first produces a context-independent question prototype for each role and then revises it to be contextually appropriate for the passage.
BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models
We introduce BitFit, a sparse-finetuning method where only the bias-terms of the model (or a subset of them) are being modified.
Thinking Like Transformers
In this paper we aim to change that, proposing a computational model for the transformer-encoder in the form of a programming language.
Neural Extractive Search
We advocate for a search paradigm called ``extractive search'', in which a search query is enriched with capture-slots, to allow for such rapid extraction.
Data Augmentation for Sign Language Gloss Translation
Sign language translation (SLT) is often decomposed into video-to-gloss recognition and gloss-to-text translation, where a gloss is a sequence of transcribed spoken-language words in the order in which they are signed.
Data Augmentation
Low-Resource Neural Machine Translation
+3
Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction
We apply this method to study how BERT models of different sizes process relative clauses (RCs).
Including Signed Languages in Natural Language Processing
Signed languages are the primary means of communication for many deaf and hard of hearing individuals.
Provable Limitations of Acquiring Meaning from Ungrounded Form: What Will Future Language Models Understand?
We study whether assertions enable a system to emulate representations preserving semantic relations like equivalence.
Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes
We explore Few-Shot Learning (FSL) for Relation Classification (RC).
Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema
To support this claim, we first show that the current evaluation method of WS is sub-optimal and propose a modification that uses twin sentences for evaluation.
Ranked #24 on
Coreference Resolution
on Winograd Schema Challenge
Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?
The cost of training such models (and the necessity of data access to do so) coupled with their utility motivates parameter sharing, i. e., the release of pretrained models such as ClinicalBERT.
Contrastive Explanations for Model Interpretability
Our method is based on projecting model representation to a latent space that captures only the features that are useful (to the model) to differentiate two potential decisions.
Bootstrapping Relation Extractors using Syntactic Search by Examples
The models also outperform models trained using NLG data augmentation techniques.
Measuring and Improving Consistency in Pretrained Language Models
In this paper we study the question: Are Pretrained Language Models (PLMs) consistent with respect to factual knowledge?
A simple geometric proof for the benefit of depth in ReLU networks
We present a simple proof for the benefit of depth in multi-layer feedforward network with rectified activation ("depth separation").
Facts2Story: Controlling Text Generation by Key Facts
Recent advancements in self-attention neural network architectures have raised the bar for open-ended text generation.
Compressing Pre-trained Language Models by Matrix Decomposition
Large pre-trained language models reach state-of-the-art results on many different NLP tasks when fine-tuned individually; They also come with a significant memory and computational requirements, calling for methods to reduce model sizes (green AI).
Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent
To better understand this bias, we study the tendency for transformer parameters to grow in magnitude ($\ell_2$ norm) during training, and its implications for the emergent representations within self attention layers.
It's not Greek to mBERT: Inducing Word-Level Translations from Multilingual BERT
Recent works have demonstrated that multilingual BERT (mBERT) learns rich cross-lingual representations, that allow for transfer across languages.
Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI
We discuss a model of trust inspired by, but not identical to, sociology's interpersonal trust (i. e., trust between people).
The Extraordinary Failure of Complement Coercion Crowdsourcing
In this work, we follow known methodologies of collecting labeled data for the complement coercion phenomenon.
Unsupervised Distillation of Syntactic Information from Contextualized Word Representations
Contextualized word representations, such as ELMo and BERT, were shown to perform well on various semantic and syntactic tasks.
Relation Classification as Two-way Span-Prediction
The current supervised relation classification (RC) task uses a single embedding to represent the relation between a pair of entities.
Ranked #1 on
Relation Extraction
on SemEval-2010 Task-8
Exposing Shallow Heuristics of Relation Extraction Models with Challenge Data
The process of collecting and annotating training data may introduce distribution artifacts which may limit the ability of models to learn correct generalization behavior.
Leap-Of-Thought: Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge
In this work, we provide a first demonstration that LMs can be trained to reliably perform systematic reasoning combining both implicit, pre-trained knowledge and explicit natural language statements.
Interactive Extractive Search over Biomedical Corpora
We present a system that allows life-science researchers to search a linguistically annotated corpus of scientific texts using patterns over dependency graphs, as well as using patterns over token sequences and a powerful variant of boolean keyword queries.
Syntactic Search by Example
A demo of the wikipedia system is available at: https://allenai. github. io/spike
Aligning Faithful Interpretations with their Social Attribution
We find that the requirement of model interpretations to be faithful is vague and incomplete.
Amnesic Probing: Behavioral Explanation with Amnesic Counterfactuals
In this work, we point out the inability to infer behavioral conclusions from probing results and offer an alternative method that focuses on how the information is being used, rather than on what information is encoded.
Nakdan: Professional Hebrew Diacritizer
We present a system for automatic diacritization of Hebrew text.
pyBART: Evidence-based Syntactic Transformations for IE
We present pyBART, an easy-to-use open-source Python library for converting English UD trees either to Enhanced UD graphs or to our representation.
A Two-Stage Masked LM Method for Term Set Expansion
We tackle the task of Term Set Expansion (TSE): given a small seed set of example terms from a semantic class, finding more members of that class.
A Formal Hierarchy of RNN Architectures
While formally extending these findings to unsaturated RNNs is left to future work, we hypothesize that the practical learnable capacity of unsaturated RNNs obeys a similar hierarchy.
Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection
The ability to control for the kinds of information encoded in neural representation has a variety of use cases, especially in light of the challenge of interpreting these models.
Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?
With the growing popularity of deep-learning based NLP models, comes a need for interpretable systems.
Unsupervised Domain Clusters in Pretrained Language Models
The notion of "in-domain data" in NLP is often over-simplistic and vague, as textual data varies in many nuanced linguistic aspects such as topic, style or level of formality.
Break It Down: A Question Understanding Benchmark
Understanding natural language questions entails the ability to break down a question into the requisite steps for computing its answer.
oLMpics -- On what Language Model Pre-training Captures
A fundamental challenge is to understand whether the performance of a LM on a task should be attributed to the pre-trained representations or to the process of fine-tuning on the task data.
How does Grammatical Gender Affect Noun Representations in Gender-Marking Languages?
Many natural languages assign grammatical gender also to inanimate nouns in the language.
Learning Deterministic Weighted Automata with Queries and Counterexamples
We present an algorithm for extraction of a probabilistic deterministic finite automaton (PDFA) from a given black-box language model, such as a recurrent neural network (RNN).
Scalable Evaluation and Improvement of Document Set Expansion via Neural Positive-Unlabeled Learning
We consider the situation in which a user has collected a small set of documents on a cohesive topic, and they want to retrieve additional documents on this topic from a large collection.
At Your Fingertips: Automatic Piano Fingering Detection
Automatic Piano Fingering is a hard task which computers can learn using data.
Improving Quality and Efficiency in Plan-based Neural Data-to-Text Generation
We follow the step-by-step approach to neural data-to-text generation we proposed in Moryossef et al (2019), in which the generation process is divided into a text-planning stage followed by a plan-realization stage.
Transfer Learning Between Related Tasks Using Expected Label Proportions
We propose a novel application of the XR framework for transfer learning between related tasks, where knowing the labels of task A provides an estimation of the label proportion of task B.
Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets
Crowdsourcing has been the prevalent paradigm for creating natural language understanding datasets in recent years.
Ab Antiquo: Neural Proto-language Reconstruction
Historical linguists have identified regularities in the process of historic sound change.
Filling Gender \& Number Gaps in Neural Machine Translation with Black-box Context Injection
When translating from a language that does not morphologically mark information such as gender and number into a language that does, translation systems must {``}guess{''} this missing information, often leading to incorrect translations in the given context.
Aligning Vector-spaces with Noisy Supervised Lexicon
The algorithm jointly learns the noise level in the lexicon, finds the set of noisy pairs, and learns the mapping between the spaces.
Towards better substitution-based word sense induction
Word sense induction (WSI) is the task of unsupervised clustering of word usages within a sentence to distinguish senses.
Ranked #1 on
Word Sense Induction
on SemEval 2010 WSI
Where's My Head? Definition, Dataset and Models for Numeric Fused-Heads Identification and Resolution
We provide the first computational treatment of fused-heads constructions (FH), focusing on the numeric fused-heads (NFH).
Ranked #1 on
Missing Elements
on Numeric Fused-Head (dev)
Towards Neural Decompilation
We address the problem of automatic decompilation, converting a program in low-level representation back to a higher-level human-readable programming language.
Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation
We propose to split the generation process into a symbolic text-planning stage that is faithful to the input, followed by a neural generation stage that focuses only on realization.
Ranked #15 on
Data-to-Text Generation
on WebNLG
Aligning Vector-spaces with Noisy Supervised Lexicons
The algorithm jointly learns the noise level in the lexicon, finds the set of noisy pairs, and learns the mapping between the spaces.
Studying the Inductive Biases of RNNs with Synthetic Variations of Natural Languages
How do typological properties such as word order and morphological case marking affect the ability of neural sequence models to acquire the syntax of a language?
Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them
Word embeddings are widely used in NLP for a vast range of tasks.
Filling Gender & Number Gaps in Neural Machine Translation with Black-box Context Injection
When translating from a language that does not morphologically mark information such as gender and number into a language that does, translation systems must "guess" this missing information, often leading to incorrect translations in the given context.
Where's My Head? Definition, Data Set, and Models for Numeric Fused-Head Identification and Resolution
We provide the first computational treatment of fused-heads constructions (FHs), focusing on the numeric fused-heads (NFHs).
A Little Is Enough: Circumventing Defenses For Distributed Learning
We show that 20% of corrupt workers are sufficient to degrade a CIFAR10 model accuracy by 50%, as well as to introduce backdoors into MNIST and CIFAR10 models without hurting their accuracy
Assessing BERT's Syntactic Abilities
I assess the extent to which the recently introduced BERT model captures English syntactic phenomena, using (1) naturally-occurring subject-verb agreement stimuli; (2) "coloreless green ideas" subject-verb agreement stimuli, in which content words in natural sentences are randomly replaced with words sharing the same part-of-speech and inflection; and (3) manually crafted stimuli for subject-verb agreement and reflexive anaphora phenomena.
Language Modeling for Code-Switching: Evaluation, Integration of Monolingual Data, and Discriminative Training
We focus on the problem of language modeling for code-switched language, in the context of automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Understanding Convolutional Neural Networks for Text Classification
We present an analysis into the inner workings of Convolutional Neural Networks (CNNs) for processing text.
Can LSTM Learn to Capture Agreement? The Case of Basque
We propose the Basque agreement prediction task as challenging benchmark for models that attempt to learn regularities in human language.
Word Sense Induction with Neural biLM and Symmetric Patterns
An established method for Word Sense Induction (WSI) uses a language model to predict probable substitutes for target words, and induces senses by clustering these resulting substitute vectors.
Adversarial Removal of Demographic Attributes from Text Data
Recent advances in Representation Learning and Adversarial Training seem to succeed in removing unwanted features from the learned representation.
SetExpander: End-to-end Term Set Expansion Based on Multi-Context Term Embeddings
We present SetExpander, a corpus-based system for expanding a seed set of terms into a more complete set of terms that belong to the same semantic class.
Term Set Expansion based on Multi-Context Term Embeddings: an End-to-end Workflow
We present SetExpander, a corpus-based system for expanding a seed set of terms into a more complete set of terms that belong to the same semantic class.
Split and Rephrase: Better Evaluation and Stronger Baselines
To aid this, we present a new train-development-test data split and neural models augmented with a copy-mechanism, outperforming the best reported baseline by 8. 68 BLEU and fostering further progress on the task.
Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translation
Despite the remarkable success of Deep RL in learning control policies from raw pixels, the resulting models do not generalize.
On the Practical Computational Power of Finite Precision RNNs for Language Recognition
While Recurrent Neural Networks (RNNs) are famously known to be Turing complete, this relies on infinite precision in the states and unbounded computation time.
Breaking NLI Systems with Sentences that Require Simple Lexical Inferences
We create a new NLI test set that shows the deficiency of state-of-the-art models in inferences that require lexical and world knowledge.
Split and Rephrase: Better Evaluation and a Stronger Baseline
To aid this, we present a new train-development-test data split and neural models augmented with a copy-mechanism, outperforming the best reported baseline by 8. 68 BLEU and fostering further progress on the task.
LaVAN: Localized and Visible Adversarial Noise
Most works on adversarial examples for deep-learning based image classifiers use noise that, while small, covers the entire image.
Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples
We do this using Angluin's L* algorithm as a learner and the trained RNN as an oracle.
From Raw Text to Universal Dependencies - Look, No Tags!
We present the Uppsala submission to the CoNLL 2017 shared task on parsing from raw text to universal dependencies.
Controlling Linguistic Style Aspects in Neural Language Generation
Most work on neural natural language generation (NNLG) focus on controlling the content of the generated text.
Exploring the Syntactic Abilities of RNNs with Multi-task Learning
Recent work has explored the syntactic abilities of RNNs using the subject-verb agreement task, which diagnoses sensitivity to sentence structure.
Greedy Transition-Based Dependency Parsing with Stack LSTMs
During training, dynamic oracles alternate between sampling parser states from the training data and from the model as it is being learned, making the model more robust to the kinds of errors that will be made at test time.
On-the-fly Operation Batching in Dynamic Computation Graphs
Dynamic neural network toolkits such as PyTorch, DyNet, and Chainer offer more flexibility for implementing models that cope with data of varying dimensions and structure, relative to toolkits that operate on statically declared computations (e. g., TensorFlow, CNTK, and Theano).
Towards String-to-Tree Neural Machine Translation
We present a simple method to incorporate syntactic information about the target language in a neural machine translation system by translating into linearized, lexicalized constituency trees.
The Interplay of Semantics and Morphology in Word Embeddings
We explore the ability of word embeddings to capture both semantic and morphological similarity, as affected by the different types of linguistic properties (surface form, lemma, morphological tag) used to compose the representation of each word.
Improving a Strong Neural Parser with Conjunction-Specific Features
While dependency parsers reach very high overall accuracy, some dependency relations are much harder than others.
DyNet: The Dynamic Neural Network Toolkit
In the static declaration strategy that is used in toolkits like Theano, CNTK, and TensorFlow, the user first defines a computation graph (a symbolic representation of the computation), and then examples are fed into an engine that executes this computation and computes its derivatives.
Semi Supervised Preposition-Sense Disambiguation using Multilingual Data
Prepositions are very common and very ambiguous, and understanding their sense is critical for understanding the meaning of the sentence.
Improving Reliability of Word Similarity Evaluation by Redesigning Annotation Task and Performance Measure
We suggest a new method for creating and using gold-standard datasets for word similarity evaluation.
Morphological Inflection Generation with Hard Monotonic Attention
We present a neural model for morphological inflection generation which employs a hard attention mechanism, inspired by the nearly-monotonic alignment commonly found between the characters in a word and the characters in its inflection.
Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies
The success of long short-term memory (LSTM) neural networks in language processing is typically attributed to their ability to capture long-distance statistical regularities.
A Neural Network for Coordination Boundary Prediction
We propose a neural-network based model for coordination boundary prediction.
A Strong Baseline for Learning Cross-Lingual Word Embeddings from Sentence Alignments
While cross-lingual word embeddings have been studied extensively in recent years, the qualitative differences between the different algorithms remain vague.
Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks
The analysis sheds light on the relative strengths of different sentence embedding methods with respect to these low level prediction tasks, and on the effect of the encoded vector's dimensionality on the resulting representations.
Coordination Annotation Extension in the Penn Tree Bank
Coordination is an important and common syntactic construction which is not handled well by state of the art parsers.
Improved Parsing for Argument-Clusters Coordination
Syntactic parsers perform poorly in prediction of Argument-Cluster Coordination (ACC).
Universal Dependencies v1: A Multilingual Treebank Collection
Cross-linguistically consistent annotation is necessary for sound comparative evaluation and cross-lingual learning experiments.
Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss
Bidirectional long short-term memory (bi-LSTM) networks have recently proven successful for various NLP sequence modeling tasks, but little is known about their reliance to input representations, target languages, data set size, and label noise.
Ranked #4 on
Part-Of-Speech Tagging
on UD
Improving sentence compression by learning to predict gaze
We show how eye-tracking corpora can be used to improve sentence compression models, presenting a novel multi-task learning algorithm based on multi-layer LSTMs.
Ranked #5 on
Sentence Compression
on Google Dataset
Improving Hypernymy Detection with an Integrated Path-based and Distributional Method
Detecting hypernymy relations is a key task in NLP, which is addressed in the literature using two complementary approaches.
Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations
The BiLSTM is trained jointly with the parser objective, resulting in very effective feature extractors for parsing.
Ranked #3 on
Chinese Dependency Parsing
on Chinese Pennbank
Training with Exploration Improves a Greedy Stack-LSTM Parser
We adapt the greedy Stack-LSTM dependency parser of Dyer et al. (2015) to support a training-with-exploration procedure using dynamic oracles(Goldberg and Nivre, 2013) instead of cross-entropy minimization.
Ranked #2 on
Chinese Dependency Parsing
on Chinese Pennbank
Getting More Out Of Syntax with PropS
Semantic NLP applications often rely on dependency trees to recognize major elements of the proposition structure of sentences.
Ranked #27 on
Open Information Extraction
on CaRB
Easy-First Dependency Parsing with Hierarchical Tree LSTMs
We suggest a compositional vector representation of parse trees that relies on a recursive combination of recurrent-neural network encoders.
A Primer on Neural Network Models for Natural Language Processing
Over the past few years, neural networks have re-emerged as powerful machine-learning models, yielding state-of-the-art results in fields such as image recognition and speech processing.
Improving Distributional Similarity with Lessons Learned from Word Embeddings
Recent trends suggest that neural-network-inspired word embedding models outperform traditional count-based distributional models on word similarity and analogy detection tasks.
Neural Word Embedding as Implicit Matrix Factorization
We analyze skip-gram with negative-sampling (SGNS), a word embedding method introduced by Mikolov et al., and show that it is implicitly factorizing a word-context matrix, whose cells are the pointwise mutual information (PMI) of the respective word and context pairs, shifted by a global constant.
word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method
The word2vec software of Tomas Mikolov and colleagues (https://code. google. com/p/word2vec/ ) has gained a lot of traction lately, and provides state-of-the-art word embeddings.
A Tabular Method for Dynamic Oracles in Transition-Based Parsing
We develop parsing oracles for two transition-based dependency parsers, including the arc-standard parser, solving a problem that was left open in (Goldberg and Nivre, 2013).
Training Deterministic Parsers with Non-Deterministic Oracles
This problem is aggravated by the fact that they are normally trained using oracles that are deterministic and incomplete in the sense that they assume a unique canonical path through the transition system and are only valid as long as the parser does not stray from this path.
