Search Results for author:
Found 73 papers, 13 papers with code
Response Construct Tagging: NLP-Aided Assessment for Engineering Education
We further investigate multi-task training on the related task of sentiment classification, which improves our model’s performance to 55 F1.
Machine Translation Between High-resource Languages in a Language Documentation Setting
This translation task is challenging for multiple reasons: (1) the data is out-of-domain with respect to the MT system’s training data, (2) much of the data is conversational, (3) existing translations include non-standard and uncommon expressions, often reflecting properties of the documented language, and (4) the data includes borrowings from other regional languages.
Open-domain Dialogue Generation: What We Can Do, Cannot Do, And Should Do Next
Human–computer conversation has long been an interest of artificial intelligence and natural language processing research.
IGT2P: From Interlinear Glossed Texts to Paradigms
An intermediate step in the linguistic analysis of an under-documented language is to find and organize inflected forms that are attested in natural speech.
Findings of the SIGMORPHON 2021 Shared Task on Unsupervised Morphological Paradigm Clustering
We describe the second SIGMORPHON shared task on unsupervised morphology: the goal of the SIGMORPHON 2021 Shared Task on Unsupervised Morphological Paradigm Clustering is to cluster word types from a raw text corpus into paradigms.
Paradigm Clustering with Weighted Edit Distance
This paper describes our system for the SIGMORPHON 2021 Shared Task on Unsupervised Morphological Paradigm Clustering, which asks participants to group inflected forms together according their underlying lemma without the aid of annotated training data.
Findings of the AmericasNLP 2021 Shared Task on Open Machine Translation for Indigenous Languages of the Americas
This paper presents the results of the 2021 Shared Task on Open Machine Translation for Indigenous Languages of the Americas.
Morphological Processing of Low-Resource Languages: Where We Are and What’s Next
Automatic morphological processing can aid downstream natural language processing applications, especially for low-resource languages, and assist language documentation efforts for endangered languages.
The World of an Octopus: How Reporting Bias Influences a Language Model’s Perception of Color
Recent work has raised concerns about the inherent limitations of text-only pretraining.
On the Automatic Generation and Simplification of Children's Stories
With recent advances in large language models (LLMs), the concept of automatically generating children's educational materials has become increasingly realistic.
Neural Machine Translation for the Indigenous Languages of the Americas: An Introduction
Neural models have drastically advanced state of the art for machine translation (MT) between high-resource languages.
Ethical Considerations for Machine Translation of Indigenous Languages: Giving a Voice to the Speakers
In recent years machine translation has become very successful for high-resource language pairs.
An Investigation of Noise in Morphological Inflection
We aim at closing this gap by investigating the types of noise encountered within a pipeline for truly unsupervised morphological paradigm completion and its impact on morphological inflection systems: First, we propose an error taxonomy and annotation pipeline for inflection training data.
Meeting the Needs of Low-Resource Languages: The Value of Automatic Alignments via Pretrained Models
However, the languages most in need of automatic alignment are low-resource and, thus, not typically included in the pretraining data.
Mind the Knowledge Gap: A Survey of Knowledge-enhanced Dialogue Systems
Many dialogue systems (DSs) lack characteristics humans have, such as emotion perception, factuality, and informativeness.
A Major Obstacle for NLP Research: Let's Talk about Time Allocation!
The field of natural language processing (NLP) has grown over the last few years: conferences have become larger, we have published an incredible amount of papers, and state-of-the-art research has been implemented in a large variety of customer-facing products.
A Comprehensive Comparison of Neural Networks as Cognitive Models of Inflection
Neural networks have long been at the center of a debate around the cognitive mechanism by which humans process inflectional morphology.
Match the Script, Adapt if Multilingual: Analyzing the Effect of Multilingual Pretraining on Cross-lingual Transferability
(2) Does the answer to that question change with model adaptation?
Morphological Processing of Low-Resource Languages: Where We Are and What's Next
Automatic morphological processing can aid downstream natural language processing applications, especially for low-resource languages, and assist language documentation efforts for endangered languages.
BPE vs. Morphological Segmentation: A Case Study on Machine Translation of Four Polysynthetic Languages
Morphologically-rich polysynthetic languages present a challenge for NLP systems due to data sparsity, and a common strategy to handle this issue is to apply subword segmentation.
The World of an Octopus: How Reporting Bias Influences a Language Model's Perception of Color
Recent work has raised concerns about the inherent limitations of text-only pretraining.
Findings of the LoResMT 2021 Shared Task on COVID and Sign Language for Low-resource Languages
Maximum system performance was computed using BLEU and follow as 36. 0 for English--Irish, 34. 6 for Irish--English, 24. 2 for English--Marathi, and 31. 3 for Marathi--English.
Proceedings of the First Workshop on Weakly Supervised Learning (WeaSuL)
Welcome to WeaSuL 2021, the First Workshop on Weakly Supervised Learning, co-located with ICLR 2021.
Don't Rule Out Monolingual Speakers: A Method For Crowdsourcing Machine Translation Data
Based on the insight that humans pay specific attention to movements, we use graphics interchange formats (GIFs) as a pivot to collect parallel sentences from monolingual annotators.
What Would a Teacher Do? Predicting Future Talk Moves
Recent advances in natural language processing (NLP) have the ability to transform how classroom learning takes place.
PROST: Physical Reasoning of Objects through Space and Time
We present a new probing dataset named PROST: Physical Reasoning about Objects Through Space and Time.
How to Adapt Your Pretrained Multilingual Model to 1600 Languages
Pretrained multilingual models (PMMs) enable zero-shot learning via cross-lingual transfer, performing best for languages seen during pretraining.
AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages
Continued pretraining offers improvements, with an average accuracy of 44. 05%.
Coloring the Black Box: What Synesthesia Tells Us about Character Embeddings
And how similar are character embeddings extracted from different models?
CLiMP: A Benchmark for Chinese Language Model Evaluation
CLiMP consists of sets of 1, 000 minimal pairs (MPs) for 16 syntactic contrasts in Mandarin, covering 9 major Mandarin linguistic phenomena.
Making a Point: Pointer-Generator Transformers for Disjoint Vocabularies
Here, we propose a model that does not: a pointer-generator transformer for disjoint vocabularies.
Tackling the Low-resource Challenge for Canonical Segmentation
Canonical morphological segmentation consists of dividing words into their standardized morphemes.
Acrostic Poem Generation
We propose a new task in the area of computational creativity: acrostic poem generation in English.
Can Wikipedia Categories Improve Masked Language Model Pretraining?
Pretrained language models have obtained impressive results for a large set of natural language understanding tasks.
Frustratingly Easy Multilingual Grapheme-to-Phoneme Conversion
In this paper, we describe two CU-Boulder submissions to the SIGMORPHON 2020 Task 1 on multilingual grapheme-to-phoneme conversion (G2P).
Intermediate-Task Transfer Learning with Pretrained Language Models: When and Why Does It Work?
However, we fail to observe more granular correlations between probing and target task performance, highlighting the need for further work on broad-coverage probing benchmarks.
The IMS--CUBoulder System for the SIGMORPHON 2020 Shared Task on Unsupervised Morphological Paradigm Completion
In this paper, we present the systems of the University of Stuttgart IMS and the University of Colorado Boulder (IMS--CUBoulder) for SIGMORPHON 2020 Task 2 on unsupervised morphological paradigm completion (Kann et al., 2020).
The NYU-CUBoulder Systems for SIGMORPHON 2020 Task 0 and Task 2
Second, as inflected forms share most characters with the lemma, we further propose a pointer-generator transformer model to allow easy copying of input characters.
The SIGMORPHON 2020 Shared Task on Unsupervised Morphological Paradigm Completion
In this paper, we describe the findings of the SIGMORPHON 2020 shared task on unsupervised morphological paradigm completion (SIGMORPHON 2020 Task 2), a novel task in the field of inflectional morphology.
Self-Training for Unsupervised Parsing with PRPN
To be able to use our model's predictions during training, we extend a recent neural UP architecture, the PRPN (Shen et al., 2018a) such that it can be trained in a semi-supervised fashion.
English Intermediate-Task Training Improves Zero-Shot Cross-Lingual Transfer Too
Intermediate-task training---fine-tuning a pretrained model on an intermediate task before fine-tuning again on the target task---often improves model performance substantially on language understanding tasks in monolingual English settings.
Ranked #20 on
Zero-Shot Cross-Lingual Transfer
on XTREME
The IMS-CUBoulder System for the SIGMORPHON 2020 Shared Task on Unsupervised Morphological Paradigm Completion
In this paper, we present the systems of the University of Stuttgart IMS and the University of Colorado Boulder (IMS-CUBoulder) for SIGMORPHON 2020 Task 2 on unsupervised morphological paradigm completion (Kann et al., 2020).
Unsupervised Morphological Paradigm Completion
We propose the task of unsupervised morphological paradigm completion.
Intermediate-Task Transfer Learning with Pretrained Models for Natural Language Understanding: When and Why Does It Work?
However, we fail to observe more granular correlations between probing and target task performance, highlighting the need for further work on broad-coverage probing benchmarks.
Learning to Learn Morphological Inflection for Resource-Poor Languages
We propose to cast the task of morphological inflection - mapping a lemma to an indicated inflected form - for resource-poor languages as a meta-learning problem.
Weakly Supervised POS Taggers Perform Poorly on Truly Low-Resource Languages
Part-of-speech (POS) taggers for low-resource languages which are exclusively based on various forms of weak supervision - e. g., cross-lingual transfer, type-level supervision, or a combination thereof - have been reported to perform almost as well as supervised ones.
Neural Unsupervised Parsing Beyond English
Recently, neural network models which automatically infer syntactic structure from raw text have started to achieve promising results.
Grammatical Gender, Neo-Whorfianism, and Word Embeddings: A Data-Driven Approach to Linguistic Relativity
The relation between language and thought has occupied linguists for at least a century.
Acquisition of Inflectional Morphology in Artificial Neural Networks With Prior Knowledge
How does knowledge of one language's morphology influence learning of inflection rules in a second one?
Towards Realistic Practices In Low-Resource Natural Language Processing: The Development Set
Here, we aim to answer the following questions: Does using a development set for early stopping in the low-resource setting influence results as compared to a more realistic alternative, where the number of training epochs is tuned on development languages?
Transductive Auxiliary Task Self-Training for Neural Multi-Task Models
Multi-task learning and self-training are two common ways to improve a machine learning model's performance in settings with limited training data.
Probing for Semantic Classes: Diagnosing the Meaning Content of Word Embeddings
Word embeddings typically represent different meanings of a word in a single conflated vector.
Subword-Level Language Identification for Intra-Word Code-Switching
Language identification for code-switching (CS), the phenomenon of alternating between two or more languages in conversations, has traditionally been approached under the assumption of a single language per token.
Verb Argument Structure Alternations in Word and Sentence Embeddings
For converging evidence, we further construct LaVA, a corresponding word-level dataset, and investigate whether the same syntactic features can be extracted from word embeddings.
The CoNLL--SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection
Apart from extending the number of languages involved in earlier supervised tasks of generating inflected forms, this year the shared task also featured a new second task which asked participants to inflect words in sentential context, similar to a cloze task.
Sentence-Level Fluency Evaluation: References Help, But Can Be Spared!
Motivated by recent findings on the probabilistic modeling of acceptability judgments, we propose syntactic log-odds ratio (SLOR), a normalized language model score, as a metric for referenceless fluency evaluation of natural language generation output at the sentence level.
Neural Transductive Learning and Beyond: Morphological Generation in the Minimal-Resource Setting
Neural state-of-the-art sequence-to-sequence (seq2seq) models often do not perform well for small training sets.
Evaluating Word Embeddings in Multi-label Classification Using Fine-grained Name Typing
We propose a new evaluation method for word embeddings based on multi-label classification given a word embedding.
Lost in Translation: Analysis of Information Loss During Machine Translation Between Polysynthetic and Fusional Languages
Machine translation from polysynthetic to fusional languages is a challenging task, which gets further complicated by the limited amount of parallel text available.
Character-level Supervision for Low-resource POS Tagging
Neural part-of-speech (POS) taggers are known to not perform well with little training data.
Fortification of Neural Morphological Segmentation Models for Polysynthetic Minimal-Resource Languages
Morphological segmentation for polysynthetic languages is challenging, because a word may consist of many individual morphemes and training data can be extremely scarce.
Exploring Cross-Lingual Transfer of Morphological Knowledge In Sequence-to-Sequence Models
Multi-task training is an effective method to mitigate the data sparsity problem.
Unlabeled Data for Morphological Generation With Character-Based Sequence-to-Sequence Models
We present a semi-supervised way of training a character-based encoder-decoder recurrent neural network for morphological reinflection, the task of generating one inflected word form from another.
One-Shot Neural Cross-Lingual Transfer for Paradigm Completion
We present a novel cross-lingual transfer method for paradigm completion, the task of mapping a lemma to its inflected forms, using a neural encoder-decoder model, the state of the art for the monolingual task.
Comparative Study of CNN and RNN for Natural Language Processing
Deep neural networks (DNN) have revolutionized the field of natural language processing (NLP).
Neural Multi-Source Morphological Reinflection
We explore the task of multi-source morphological reinflection, which generalizes the standard, single-source version.
Single-Model Encoder-Decoder with Explicit Morphological Representation for Reinflection
Morphological reinflection is the task of generating a target form given a source form, a source tag and a target tag.
