Search Results for author:
Found 30 papers, 8 papers with code
Less is More: Attention Supervision with Counterfactuals for Text Classification
We aim to leverage human and machine intelligence together for attention supervision.
Robustifying Multi-hop QA through Pseudo-Evidentiality Training
This paper studies the bias problem of multi-hop question answering models, of answering correctly without correct reasoning.
Query Generation for Multimodal Documents
This paper studies the problem of generatinglikely queries for multimodal documents withimages.
Meta-path Free Semi-supervised Learning for Heterogeneous Networks
Graph neural networks (GNNs) have been widely used in representation learning on graphs and achieved superior performance in tasks such as node classification.
SQuAD2-CR: Semi-supervised Annotation for Cause and Rationales for Unanswerability in SQuAD 2.0
Existing machine reading comprehension models are reported to be brittle for adversarially perturbed questions when optimizing only for accuracy, which led to the creation of new reading comprehension benchmarks, such as SQuAD 2. 0 which contains such type of questions.
Learning with Limited Data for Multilingual Reading Comprehension
This paper studies the problem of supporting question answering in a new language with limited training resources.
NL2pSQL: Generating Pseudo-SQL Queries from Under-Specified Natural Language Questions
Here we describe a new NL2pSQL task to generate pSQL codes from natural language questions on under-specified database issues, NL2pSQL.
MICRON: Multigranular Interaction for Contextualizing RepresentatiON in Non-factoid Question Answering
This paper studies the problem of non-factoid question answering, where the answer may span over multiple sentences.
Evaluating Research Novelty Detection: Counterfactual Approaches
We find the novelty is not a singular concept, and thus inherently lacks of ground truth annotations with cross-annotator agreement, which is a major obstacle in evaluating these models.
Text Length Adaptation in Sentiment Classification
We propose a state-of-the-art CLT model called Length Transfer Networks (LeTraNets) that introduces a two-way encoding scheme for short and long texts using multiple training mechanisms.
Soft Representation Learning for Sparse Transfer
Transfer learning is effective for improving the performance of tasks that are related, and Multi-task learning (MTL) and Cross-lingual learning (CLL) are important instances.
KBQA: Learning Question Answering over QA Corpora and Knowledge Bases
Based on these templates, our QA system KBQA effectively supports binary factoid questions, as well as complex questions which are composed of a series of binary factoid questions.
Categorical Metadata Representation for Customized Text Classification
The performance of text classification has improved tremendously using intelligently engineered neural-based models, especially those injecting categorical metadata as additional information, e. g., using user/product information for sentiment classification.
Ranked #2 on
Sentiment Analysis
on User and product information
(Yelp 2013 (Acc) metric)
QADiver: Interactive Framework for Diagnosing QA Models
Question answering (QA) extracting answers from text to the given question in natural language, has been actively studied and existing models have shown a promise of outperforming human performance when trained and evaluated with SQuAD dataset.
AutoSense Model for Word Sense Induction
Thus, we aim to eliminate these requirements and solve the sense granularity problem by proposing AutoSense, a latent variable model based on two observations: (1) senses are represented as a distribution over topics, and (2) senses generate pairings between the target word and its neighboring word.
Ranked #2 on
Word Sense Induction
on SemEval 2010 WSI
Adversarial TableQA: Attention Supervision for Question Answering on Tables
The same question has not been asked in the table question answering (TableQA) task, where we are tasked to answer a query given a table.
Mining Cross-Cultural Differences and Similarities in Social Media
Cross-cultural differences and similarities are common in cross-lingual natural language understanding, especially for research in social media.
Translations as Additional Contexts for Sentence Classification
We are the first to use translations as domain-free contexts for sentence classification.
Ranked #5 on
Text Classification
on TREC-6
Entity Commonsense Representation for Neural Abstractive Summarization
To this end, we leverage on an off-the-shelf entity linking system (ELS) to extract linked entities and propose Entity2Topic (E2T), a module easily attachable to a sequence-to-sequence model that transforms a list of entities into a vector representation of the topic of the summary.
Ranked #17 on
Text Summarization
on GigaWord
Aspect Sentiment Model for Micro Reviews
This paper aims at an aspect sentiment model for aspect-based sentiment analysis (ABSA) focused on micro reviews.
Cold-Start Aware User and Product Attention for Sentiment Classification
The use of user/product information in sentiment analysis is important, especially for cold-start users/products, whose number of reviews are very limited.
Ranked #2 on
Sentiment Analysis
on User and product information
Verb Pattern: A Probabilistic Semantic Representation on Verbs
In this paper, we introduce verb patterns to represent verbs' semantics, such that each pattern corresponds to a single semantic of the verb.
Probabilistic Prototype Model for Serendipitous Property Mining
Besides providing the relevant information, amusing users has been an important role of the web.
Entity Suggestion by Example using a Conceptual Taxonomy
This paper provides a query processing method based on the relevance models between entity sets and concepts.
