Search Results for author:
Found 30 papers, 13 papers with code
Online Neural Coreference Resolution with Rollback
Humans process natural language online, whether reading a document or participating in multiparty dialogue.
Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass
In StreamingQA, our approach is effective in injecting knowledge into the LM's parameters, achieving a 63. 5% improvement in F1 score over the model with supervised fine-tuning (from $19. 5$ to $31. 5$) for contexts as long as 32K tokens.
Multi-Field Adaptive Retrieval
Document retrieval for tasks such as search and retrieval-augmented generation typically involves datasets that are unstructured: free-form text without explicit internal structure in each document.
SMART: Self-learning Meta-strategy Agent for Reasoning Tasks
This inefficiency raises the question: Can LMs learn to select the optimal strategy in the first attempt, without a need for refinement?
Learning to Retrieve Iteratively for In-Context Learning
We introduce iterative retrieval, a novel framework that empowers retrievers to make iterative decisions through policy optimization.
Interpreting User Requests in the Context of Natural Language Standing Instructions
Users of natural language interfaces, generally powered by Large Language Models (LLMs), often must repeat their preferences each time they make a similar request.
SCREWS: A Modular Framework for Reasoning with Revisions
To enable exploration in this space, we present SCREWS, a modular framework for reasoning with revisions.
Few-Shot Adaptation for Parsing Contextual Utterances with LLMs
We evaluate the ability of semantic parsers based on large language models (LLMs) to handle contextual utterances.
Natural Language Decomposition and Interpretation of Complex Utterances
Designing natural language interfaces has historically required collecting supervised data to translate user requests into carefully designed intent representations.
Automatic Document Selection for Efficient Encoder Pretraining
Building pretrained language models is considered expensive and data-intensive, but must we increase dataset size to achieve better performance?
Multilingual Coreference Resolution in Multiparty Dialogue
Existing multiparty dialogue datasets for entity coreference resolution are nascent, and many challenges are still unaddressed.
Pruning Pretrained Encoders with a Multitask Objective
The sizes of pretrained language models make them challenging and expensive to use when there are multiple desired downstream tasks.
On Generalization in Coreference Resolution
While coreference resolution is defined independently of dataset domain, most models for performing coreference resolution do not transfer well to unseen domains.
Ranked #1 on
Coreference Resolution
on Quizbowl
Moving on from OntoNotes: Coreference Resolution Model Transfer
Academic neural models for coreference resolution (coref) are typically trained on a single dataset, OntoNotes, and model improvements are benchmarked on that same dataset.
Adapting Coreference Resolution Models through Active Learning
Active learning mitigates this problem by sampling a small subset of data for annotators to label.
LOME: Large Ontology Multilingual Extraction
We present LOME, a system for performing multilingual information extraction.
CopyNext: Explicit Span Copying and Alignment in Sequence to Sequence Models
Copy mechanisms are employed in sequence to sequence models (seq2seq) to generate reproductions of words from the input to the output.
Which *BERT? A Survey Organizing Contextualized Encoders
Pretrained contextualized text encoders are now a staple of the NLP community.
UniMorph 3.0: Universal Morphology
The project comprises two major thrusts: a language-independent feature schema for rich morphological annotation and a type-level resource of annotated data in diverse languages realizing that schema.
Incremental Neural Coreference Resolution in Constant Memory
We investigate modeling coreference resolution under a fixed memory constraint by extending an incremental clustering algorithm to utilize contextualized encoders and neural components.
Multi-Sentence Argument Linking
We present a novel document-level model for finding argument spans that fill an event's roles, connecting related ideas in sentence-level semantic role labeling and coreference resolution.
Improved Lexically Constrained Decoding for Translation and Monolingual Rewriting
Lexically-constrained sequence decoding allows for explicit positive or negative phrase-based constraints to be placed on target output strings in generation tasks such as machine translation or monolingual text rewriting.
What do you learn from context? Probing for sentence structure in contextualized word representations
The jiant toolkit for general-purpose text understanding models
Looking for ELMo's friends: Sentence-Level Pretraining Beyond Language Modeling
Work on the problem of contextualized word representation—the development of reusable neural network components for sentence understanding—has recently seen a surge of progress centered on the unsupervised pretraining task of language modeling with methods like ELMo (Peters et al., 2018).
Probing What Different NLP Tasks Teach Machines about Function Word Comprehension
Our results show that pretraining on language modeling performs the best on average across our probing tasks, supporting its widespread use for pretraining state-of-the-art NLP models, and CCG supertagging and NLI pretraining perform comparably.
Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling
Natural language understanding has recently seen a surge of progress with the use of sentence encoders like ELMo (Peters et al., 2018a) and BERT (Devlin et al., 2019) which are pretrained on variants of language modeling.
UniMorph 2.0: Universal Morphology
The Universal Morphology UniMorph project is a collaborative effort to improve how NLP handles complex morphology across the world's languages.
Deriving Consensus for Multi-Parallel Corpora: an English Bible Study
We present a method which generates a single consensus between multi-parallel corpora.
CoNLL-SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection in 52 Languages
In sub-task 2, systems were given a lemma and some of its specific inflected forms, and asked to complete the inflectional paradigm by predicting all of the remaining inflected forms.
Annotating Character Relationships in Literary Texts
We present a dataset of manually annotated relationships between characters in literary texts, in order to support the training and evaluation of automatic methods for relation type prediction in this domain (Makazhanov et al., 2014; Kokkinakis, 2013) and the broader computational analysis of literary character (Elson et al., 2010; Bamman et al., 2014; Vala et al., 2015; Flekova and Gurevych, 2015).
