Papers by Tom Kwiatkowski

12 papers
MOLEMAN: Mention-Only Linking of Entities with a Mention Annotation Network (2021.acl-short)

Copied to clipboard

Challenge: Existing approaches to entity linking represent each entity with a single vector, but instead use a contextualized mention-encoder that learns to place similar mentions of the same entity closer in vector space than mentions from different entities.
Approach: They propose an instance-based nearest neighbor approach to entity linking that allows for a contextualized mention-encoder to learn to place similar mentions of the same entity closer in vector space than mentions from different entities.
Outcome: The proposed approach outperforms all other systems on two multilingual benchmarks and is simpler to train and interpretable.
BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions (N19-1)

Copied to clipboard

Challenge: In this paper we build a reading comprehension dataset of yes/no questions that are naturally occurring . they often query for complex, non-factoid information, and require difficult entailment-like inference to solve.
Approach: They build a reading comprehension dataset of yes/no questions that are naturally occurring . they find they are unexpectedly challenging and require difficult inferences to solve .
Outcome: The proposed method achieves 80.4% accuracy compared to 90% accuracy of human annotators and 62% majority-baseline.
Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index (P19-1)

Copied to clipboard

Challenge: Existing open-domain question answering models require multiple documents on-demand for every input query.
Approach: They propose query-agnostic indexable representations of document phrases that can drastically speed up open-domain question answering.
Outcome: The proposed model can be trained and deployed even in a single 4-GPU server.
Phrase-Indexed Question Answering: A New Challenge for Scalable Document Comprehension (D18-1)

Copied to clipboard

Challenge: Existing QA models rely on learning interaction between document and question . current models require explicit attention to the document before or as it reads it .
Approach: They propose a modular question answering task that enforces complete independence of the document encoder from the question encoder.
Outcome: The proposed model achieves reasonable accuracy but significantly underperforms unconstrained QA models.
Evaluating and Modeling Attribution for Cross-Lingual Question Answering (2023.emnlp-main)

Copied to clipboard

Challenge: Open-retrieval question answering systems are lacking in attribution for cross-lingual question answering . open-research questions are available in 20 languages, but their raw generation often falls short in factuality .
Approach: They are the first to study attribution for cross-lingual question answering . they collect data in 5 languages to assess the attribution level of a state-of-the-art QA system .
Outcome: The proposed approach improves the attribution level of a state-of-the-art cross-lingual QA system.
Matching the Blanks: Distributional Similarity for Relation Learning (P19-1)

Copied to clipboard

Challenge: Efforts to build general purpose relation extractors that can model arbitrary relations are limited in their ability to generalize.
Approach: They propose to build task-agnostic relation representations solely from entity-linked text to extend Harris’ distributional hypothesis to relations.
Outcome: The proposed representations outperform previous methods on SemEval 2010 Task 8, KBP37, and TACRED even without using any of the task’s training data.
Decontextualization: Making Sentences Stand-Alone (2021.tacl-1)

Copied to clipboard

Challenge: Taking excerpts of text can be problematic, as key pieces may not be explicit in a local window.
Approach: They define a problem of sentence decontextualization by rewriting a sentence to be interpretable out of context while preserving its meaning.
Outcome: The proposed method can be used in question answering and document understanding tasks.
TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages (2020.tacl-1)

Copied to clipboard

Challenge: Existing models for multilingual modeling are based on a set of typological features that are used to express meaning in languages such as English.
Approach: They present a question-answer-typed question-referenced dataset that covers 11 typologically diverse languages with 204K question-and-answered pairs.
Outcome: The proposed dataset covers 11 typologically diverse languages with 204K question-answer pairs.
NAIL: Lexical Retrieval Indices with Efficient Non-Autoregressive Decoders (2023.emnlp-main)

Copied to clipboard

Challenge: Neural document rerankers require dedicated hardware for serving, which is costly and often not feasible.
Approach: They propose a method that captures 86% of the gains of a Transformer cross-attention model with a lexicalized scoring function that only requires 10-6% of . the model architecture is compatible with recent encoder-decoder and decoder-only large language models, such as T5, GPT-3 and PaLM.
Outcome: The proposed model captures 86% of the gains of a Transformer cross-attention model with a lexicalized scoring function.
1-PAGER: One Pass Answer Generation and Evidence Retrieval (2023.findings-emnlp)

Copied to clipboard

Challenge: 1-Pager is the first system that answers a question and retrieves evidence using a single Transformer-based model and decoding process.
Approach: They propose a system that partitions the corpus using constrained decoding to select a document and answer string, and a method that uses a single Transformer-based model to generate evidence.
Outcome: The proposed system outperforms the equivalent ‘closed-book’ question answering model by grounding predictions in evidence corpus.
From RAG to Riches: Retrieval Interlaced with Sequence Generation (2024.emnlp-main)

Copied to clipboard

Challenge: RICHES interleaves retrieval with sequence generation tasks . traditional approaches chain LLM generation with separate retrieval model .
Approach: They propose a novel approach that interleaves retrieval with sequence generation tasks . they propose attributed evidence, multi-hop retrievals and interleave thoughts to plan on what to retrieve next .
Outcome: The proposed approach can work with any Instruction-tuned model, without additional training.
Entities as Experts: Sparse Memory Access with Entity Supervision (2020.emnlp-main)

Copied to clipboard

Challenge: Unlike previous attempts to integrate entity knowledge into sequence models, EaE’s entity representations are learned directly from text.
Approach: They propose a model that can access distinct memories of entities mentioned in a piece of text and a new architecture that can do this.
Outcome: The proposed model outperforms an encoder-generator Transformer model with 10x the parameters on a task that requires 10x more parameters to answer.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations