398 citations · 2.8k across the 98 of their papers we have counts for
69 papers · 1 filter
Comparing Neighbors Together Makes it Easy: Jointly Comparing Multiple Candidates for Efficient and Effective Retrieval
Jonghyun Song, Cheyon Jin, Wenlong Zhao +2
A common retrieve-and-rerank paradigm involves retrieving relevant candidates from a broad set using a fast bi-encoder (BE), followed by applying expensive but accurate cross-encod…
Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond
Haw-Shiuan Chang, Zonghai Yao, Alolika Gon +2
Is the output softmax layer, which is adopted by most language models (LMs), always the best way to compute the next word probability? Given so many attention layers in a modern tr…
Machine Reading Comprehension using Case-based Reasoning
Dung Thai, Dhruv Agarwal, Mudit Chaudhary +6
We present an accurate and interpretable method for answer extraction in machine reading comprehension that is reminiscent of case-based reasoning (CBR) from classical AI. Our meth…
Low-Resource Compositional Semantic Parsing with Concept Pretraining
Subendhu Rongali, Mukund Sridhar, Haidar Khan +3
Semantic parsing plays a key role in digital voice assistants such as Alexa, Siri, and Google Assistant by mapping natural language to structured meaning representations. When we w…
You can't pick your neighbors, or can you? When and how to rely on retrieval in the NN-LM
Andrew Drozdov, Shufan Wang, Razieh Rahimi +3
Retrieval-enhanced language models (LMs), which condition their predictions on text retrieved from large external datastores, have recently shown significant perplexity improvement…
Efficient Nearest Neighbor Search for Cross-Encoder Models using Matrix Factorization
Nishant Yadav, Nicholas Monath, Rico Angell +2
Efficient k-nearest neighbor search is a fundamental task, foundational for many problems in NLP. When the similarity is measured by dot-product between dual-encoder vectors or $\e…
Longtonotes: OntoNotes with Longer Coreference Chains
Kumar Shridhar, Nicholas Monath, Raghuveer Thirukovalluru +4
Ontonotes has served as the most important benchmark for coreference resolution. However, for ease of annotation, several long documents in Ontonotes were split into smaller parts.…
Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling
Haw-Shiuan Chang, Ruei-Yao Sun, Kathryn Ricci +1
Ensembling BERT models often significantly improves accuracy, but at the cost of significantly more computation and memory footprint. In this work, we propose Multi-CLS BERT, a nov…
Inducing and Using Alignments for Transition-based AMR Parsing
Andrew Drozdov, Jiawei Zhou, Radu Florian +4
Transition-based parsers for Abstract Meaning Representation (AMR) rely on node-to-word alignments. These alignments are learned separately from parser training and require a compl…
CBR-iKB: A Case-Based Reasoning Approach for Question Answering over Incomplete Knowledge Bases
Dung Thai, Srinivas Ravishankar, Ibrahim Abdelaziz +7
Knowledge bases (KBs) are often incomplete and constantly changing in practice. Yet, in many question answering applications coupled with knowledge bases, the sparse nature of KBs…
A Distant Supervision Corpus for Extracting Biomedical Relationships Between Chemicals, Diseases and Genes
Dongxu Zhang, Sunil Mohan, Michaela Torkar +1
We introduce ChemDisGene, a new dataset for training and evaluating multi-class multi-label document-level biomedical relation extraction models. Our dataset contains 80k biomedica…
Knowledge Base Question Answering by Case-based Reasoning over Subgraphs
Rajarshi Das, Ameya Godbole, Ankita Naik +5
Question answering (QA) over knowledge bases (KBs) is challenging because of the diverse, essentially unbounded, types of reasoning patterns needed. However, we hypothesize in a la…
Diverse Distributions of Self-Supervised Tasks for Meta-Learning in NLP
Trapit Bansal, Karthick Gunasekaran, Tong Wang +2
Meta-learning considers the problem of learning an efficient learning process that can leverage its past experience to accurately solve new tasks. However, the efficacy of meta-lea…
Improved Latent Tree Induction with Distant Supervision via Span Constraints
Zhiyang Xu, Andrew Drozdov, Jay Yoon Lee +6
For over thirty years, researchers have developed and analyzed methods for latent tree induction as an approach for unsupervised syntactic parsing. Nonetheless, modern systems stil…
DISAPERE: A Dataset for Discourse Structure in Peer Review Discussions
Neha Kennard, Tim O'Gorman, Rajarshi Das +6
At the foundation of scientific evaluation is the labor-intensive process of peer review. This critical task requires participants to consume vast amounts of highly technical text.…
Box Embeddings: An open-source library for representation learning using geometric structures
Tejas Chheda, Purujit Goyal, Trang Tran +4
A major factor contributing to the success of modern representation learning is the ease of performing various vector operations. Recently, objects with geometric structures (eg. d…
Entity Linking and Discovery via Arborescence-based Supervised Clustering
Dhruv Agarwal, Rico Angell, Nicholas Monath +1
Previous work has shown promising results in performing entity linking by measuring not only the affinities between mentions and entities but also those amongst mentions. In this p…
Word2Box: Capturing Set-Theoretic Semantics of Words using Box Embeddings
Shib Sankar Dasgupta, Michael Boratko, Siddhartha Mishra +4
Learning representations of words in a continuous space is perhaps the most fundamental task in NLP, however words interact in ways much richer than vector dot product similarity c…
Case-based Reasoning for Natural Language Queries over Knowledge Bases
Rajarshi Das, Manzil Zaheer, Dung Thai +6
It is often challenging to solve a complex problem from scratch, but much easier if we can access other similar problems with their solutions -- a paradigm known as case-based reas…
Multi-facet Universal Schema
Rohan Paul, Haw-Shiuan Chang, Andrew McCallum
Universal schema (USchema) assumes that two sentence patterns that share the same entity pairs are similar to each other. This assumption is widely adopted for solving various type…
Changing the Mind of Transformers for Topically-Controllable Language Generation
Haw-Shiuan Chang, Jiaming Yuan, Mohit Iyyer +1
Large Transformer-based language models can aid human authors by suggesting plausible continuations of text written so far. However, current interactive writing assistants do not a…
Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic Applications
Haw-Shiuan Chang, Amol Agrawal, Andrew McCallum
Most unsupervised NLP models represent each word with a single point or single region in semantic space, while the existing multi-sense word embeddings cannot represent longer word…
Long Document Summarization in a Low Resource Setting using Pretrained Language Models
Ahsaas Bajaj, Pavitra Dangati, Kalpesh Krishna +7
Abstractive summarization is the task of compressing a long document into a coherent short document while retaining salient information. Modern abstractive summarization methods ar…
Low Resource Recognition and Linking of Biomedical Concepts from a Large Ontology
Sunil Mohan, Rico Angell, Nick Monath +1
Tools to explore scientific literature are essential for scientists, especially in biomedicine, where about a million new papers are published every year. Many such tools provide u…