Skip to main content ->
Ai2

Research - Papers

Explore a selection of our published work on a variety of key research challenges in AI.

Filter papers

Knowledge Enhanced Contextual Word Representations

Matthew E. PetersMark NeumannRobert L. Loganand Noah A. Smith
2019
EMNLP

Contextual word representations, typically trained on unstructured, unlabeled text, do not contain any explicit grounding to real world entities and are often unable to remember facts about those… 

Language Modeling for Code-Switching: Evaluation, Integration of Monolingual Data, and Discriminative Training

Hila GonenYoav Goldberg
2019
EMNLP

We focus on the problem of language modeling for code-switched language, in the context of automatic speech recognition (ASR). Language modeling for code-switched language is challenging for (at… 

Low-Resource Parsing with Crosslingual Contextualized Representations

Phoebe MulcaireJungo KasaiNoah A. Smith
2019
CoNLL

Despite advances in dependency parsing, languages with small treebanks still present challenges. We assess recent approaches to multilingual contextual word representations (CWRs), and compare them… 

Mixture Content Selection for Diverse Sequence Generation

Jaemin ChoMinjoon SeoHannaneh Hajishirzi
2019
EMNLP

Generating diverse sequences is important in many NLP applications such as question generation or summarization that exhibit semantically one-to-many relationships between source and the target… 

On the Limits of Learning to Actively Learn Semantic Representations

Omri KoshorekGabriel StanovskyYichu ZhouVivek Srikumar and Jonathan Berant
2019
CoNLL

One of the goals of natural language understanding is to develop models that map sentences into meaning representations. However, training such models requires expensive annotation of complex… 

PaLM: A Hybrid Parser and Language Model

Hao PengRoy SchwartzNoah A. Smith
2019
EMNLP

We present PaLM, a hybrid parser and neural language model. Building on an RNN language model, PaLM adds an attention layer over text spans in the left context. An unsupervised constituency parser… 

Pretrained Language Models for Sequential Sentence Classification

Arman CohanIz BeltagyDaniel KingDaniel S. Weld
2019
EMNLP

As a step toward better document-level understanding, we explore classification of a sequence of sentences into their corresponding categories, a task that requires understanding sentences in… 

QuaRTz: An Open-Domain Dataset of Qualitative Relationship Questions

Oyvind TafjordMatt GardnerKevin LinPeter Clark
2019
EMNLP

We introduce the first open-domain dataset, called QuaRTz, for reasoning about textual qualitative relationships. QuaRTz contains general qualitative statements, e.g., "A sunscreen with a higher SPF… 

Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning

Pradeep DasigiNelson F. LiuAna MarasovicMatt Gardner
2019
EMNLP

Machine comprehension of texts longer than a single sentence often requires coreference resolution. However, most current reading comprehension benchmarks do not contain complex coreferential… 

RNN Architecture Learning with Sparse Regularization

Jesse DodgeRoy SchwartzHao PengNoah A. Smith
2019
EMNLP

Neural models for NLP typically use large numbers of parameters to reach state-of-the-art performance, which can lead to excessive memory usage and increased runtime. We present a structure learning…