Search Results for author:
Found 25 papers, 4 papers with code
Seeing the World through Text: Evaluating Image Descriptions for Commonsense Reasoning in Machine Reading Comprehension
Despite recent achievements in natural language understanding, reasoning over commonsense knowledge still represents a big challenge to AI systems.
Scene-Text Aware Image and Text Retrieval with Dual-Encoder
We tackle the tasks of image and text retrieval using a dual-encoder model in which images and text are encoded independently.
InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions
We study the problem of completing various visual document understanding (VDU) tasks, e. g., question answering and information extraction, on real-world documents through human-written instructions.
Robust Text-driven Image Editing Method that Adaptively Explores Directions in Latent Spaces of StyleGAN and CLIP
Our model represents the edit direction as a normal vector in the CLIP space obtained by training a SVM to classify positive and negative images.
SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images
Visual question answering on document images that contain textual, visual, and layout information, called document VQA, has received much attention recently.
Self-Adaptive Named Entity Recognition by Retrieving Unstructured Knowledge
Although named entity recognition (NER) helps us to extract domain-specific entities from text (e. g., artists in the music domain), it is costly to create a large amount of training data or a structured knowledge base to perform accurate NER in the target domain.
Improving Few-Shot Image Classification Using Machine- and User-Generated Natural Language Descriptions
Our proposed model, LIDE (Learning from Image and DEscription), has a text decoder to generate the descriptions and a text encoder to obtain the text representations of machine- or user-generated descriptions.
Towards Interpretable and Reliable Reading Comprehension: A Pipeline Model with Unanswerability Prediction
In this study, we define an interpretable reading comprehension (IRC) model as a pipeline model with the capability of predicting unanswerable queries.
Task-adaptive Pre-training of Language Models with Word Embedding Regularization
TAPTER runs additional pre-training by making the static word embeddings of a PTLM close to the word embeddings obtained in the target domain with fastText.
VisualMRC: Machine Reading Comprehension on Document Images
In this study, we introduce a new visual machine reading comprehension dataset, named VisualMRC, wherein given a question and a document image, a machine reads and comprehends texts in the image to answer the question in natural language.
Machine Reading Comprehension
Natural Language Understanding
+2
A Transformer-based Audio Captioning Model with Keyword Estimation
TRACKE estimates keywords, which comprise a word set corresponding to audio events/scenes in the input audio, and generates the caption while referring to the estimated keywords to reduce word-selection indeterminacy.
Abstractive Summarization with Combination of Pre-trained Sequence-to-Sequence and Saliency Models
Experimental results showed that most of the combination models outperformed a simple fine-tuned seq-to-seq model on both the CNN/DM and XSum datasets even if the seq-to-seq model is pre-trained on large-scale corpora.
Length-controllable Abstractive Summarization by Guiding with Summary Prototype
Unlike the previous models, our length-controllable abstractive summarization model incorporates a word-level extractive module in the encoder-decoder model instead of length embeddings.
Unsupervised Domain Adaptation of Language Models for Reading Comprehension
The second one is the proposed model that uses a multi-task learning approach of LM and RC.
A Simple but Effective Method to Incorporate Multi-turn Context with BERT for Conversational Machine Comprehension
Conversational machine comprehension (CMC) requires understanding the context of multi-turn dialogue.
Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extraction
It enables QFE to consider the dependency among the evidence sentences and cover important information in the question sentence.
Ranked #61 on
Question Answering
on HotpotQA
Multi-style Generative Reading Comprehension
Second, whereas previous studies built a specific model for each answer style because of the difficulty of acquiring one general model, our approach learns multi-style answers within a model to improve the NLG capability for all styles involved.
Ranked #1 on
Question Answering
on MS MARCO
Commonsense Knowledge Base Completion and Generation
To improve the accuracy of CKB completion and expand the size of CKBs, we formulate a new commonsense knowledge base generation task (CKB generation) and propose a joint learning method that incorporates both CKB completion and CKB generation.
Retrieve-and-Read: Multi-task Learning of Information Retrieval and Reading Comprehension
Previous MRS studies, in which the IR component was trained without considering answer spans, struggled to accurately find a small number of relevant passages from a large set of passages.
Natural Language Inference with Definition Embedding Considering Context On the Fly
Natural language inference (NLI) is one of the most important tasks in NLP.
Improving Neural Text Normalization with Data Augmentation at Character- and Morphological Levels
In this study, we investigated the effectiveness of augmented data for encoder-decoder-based neural normalization models.
Hyperspherical Query Likelihood Models with Word Embeddings
In addition, this paper reveals relationships between hyperspherical QLMs and conventional QLMs.
Automatically Extracting Variant-Normalization Pairs for Japanese Text Normalization
Social media texts, such as tweets from Twitter, contain many types of non-standard tokens, and the number of normalization approaches for handling such noisy text has been increasing.
A Hierarchical Neural Network for Information Extraction of Product Attribute and Condition Sentences
This paper describes a hierarchical neural network we propose for sentence classification to extract product information from product documents.
Learning and Detecting Concept Drift
When concept drift is detected, the online classifier is reinitialized to prepare for the learning of the next concept.
