Search Results for author:
Found 38 papers, 26 papers with code
Findings of the 2021 Conference on Machine Translation (WMT21)
This paper presents the results of the newstranslation task, the multilingual low-resourcetranslation for Indo-European languages, thetriangular translation task, and the automaticpost-editing task organised as part of the Con-ference on Machine Translation (WMT) 2021. In the news task, participants were asked tobuild machine translation systems for any of10 language pairs, to be evaluated on test setsconsisting mainly of news stories.
Non-autoregressive Translation with Disentangled Context Transformer
State-of-the-art neural machine translation models generate a translation from left to right and every step is conditioned on the previously generated tokens.
TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering
We introduce TIFA (Text-to-Image Faithfulness evaluation with question Answering), an automatic evaluation metric that measures the faithfulness of a generated image to its text input via visual question answering (VQA).
Batch Prompting: Efficient Inference with Large Language Model APIs
We extensively validate the effectiveness of batch prompting on ten datasets across commonsense QA, arithmetic reasoning, and NLI/NLU: batch prompting significantly~(up to $5\times$ with six samples in batch) reduces the LLM (Codex) inference token and time costs while achieving better or comparable performance.
NarrowBERT: Accelerating Masked Language Model Pretraining and Inference
We propose NarrowBERT, a modified transformer encoder that increases the throughput for masked language model pretraining by more than $2\times$.
One Embedder, Any Task: Instruction-Finetuned Text Embeddings
Our analysis suggests that INSTRUCTOR is robust to changes in instructions, and that instruction finetuning mitigates the challenge of training a single model on diverse datasets.
BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting
The BLOOM model is a large open-source multilingual language model capable of zero-shot learning, but its pretraining was limited to 46 languages.
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions.
How Much Does Attention Actually Attend? Questioning the Importance of Attention in Pretrained Transformers
Our results motivate research on simpler alternatives to input-dependent attention, as well as on methods for better utilization of this mechanism in the Transformer architecture.
Selective Annotation Makes Language Models Better Few-Shot Learners
Departing from recent in-context learning methods, we formulate an annotation-efficient, two-step framework: selective annotation that chooses a pool of examples to annotate from unlabeled data in advance, followed by prompt retrieval that retrieves task examples from the annotated pool at test time.
FOLIO: Natural Language Reasoning with First-Order Logic
We present FOLIO, a human-annotated, open-domain, and logically complex and diverse dataset for reasoning in natural language (NL), equipped with first order logic (FOL) annotations.
RealTime QA: What's the Answer Right Now?
We introduce RealTime QA, a dynamic question answering (QA) platform that announces questions and evaluates systems on a regular basis (weekly in this version).
MIA 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languages
We present the results of the Workshop on Multilingual Information Access (MIA) 2022 Shared Task, evaluating cross-lingual open-retrieval question answering (QA) systems in 16 typologically diverse languages.
Twist Decoding: Diverse Generators Guide Each Other
Our extensive evaluations on machine translation and scientific paper summarization demonstrate that Twist decoding substantially outperforms each model decoded in isolation over various scenarios, including cases where domain-specific and general-purpose models are both available.
Beam Decoding with Controlled Patience
Text generation with beam search has proven successful in a wide range of applications.
NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics
To enable constrained generation, we build on NeuroLogic decoding (Lu et al., 2021), combining its flexibility in incorporating logical constraints with A*esque estimates of future constraint satisfaction.
Ranked #1 on
Text Generation
on ROCStories
Bidimensional Leaderboards: Generate and Evaluate Language Hand in Hand
We therefore propose a generalization of leaderboards, bidimensional leaderboards (Billboards), that simultaneously tracks progress in language generation models and metrics for their evaluation.
Transparent Human Evaluation for Image Captioning
We establish THumB, a rubric-based human evaluation protocol for image captioning models.
ABC: Attention with Bounded-memory Control
One way to improve the efficiency is to bound the memory size.
One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval
We present Cross-lingual Open-Retrieval Answer Generation (CORA), the first unified many-to-many question answering (QA) model that can answer questions across many languages, even for ones without language-specific annotated data or knowledge sources.
Probing Across Time: What Does RoBERTa Know and When?
Models of language trained on very large corpora have been demonstrated useful for NLP.
Finetuning Pretrained Transformers into RNNs
Specifically, we propose a swap-then-finetune procedure: in an off-the-shelf pretrained transformer, we replace the softmax attention with its linear-complexity recurrent alternative and then finetune.
Ranked #2 on
Machine Translation
on WMT2017 Chinese-English
GENIE: Toward Reproducible and Standardized Human Evaluation for Text Generation
While often assumed a gold standard, effective human evaluation of text generation remains an important, open area for research.
XOR QA: Cross-lingual Open-Retrieval Question Answering
Multilingual question answering tasks typically assume answers exist in the same language as the question.
Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Translation
We show that the speed disadvantage for autoregressive baselines compared to non-autoregressive methods has been overestimated in three aspects: suboptimal layer allocation, insufficient speed measurement, and lack of knowledge distillation.
Non-Autoregressive Machine Translation with Disentangled Context Transformer
State-of-the-art neural machine translation models generate a translation from left to right and every step is conditioned on the previously generated tokens.
Cracking the Contextual Commonsense Code: Understanding Commonsense Reasoning Aptitude of Deep Contextual Representations
Pretrained deep contextual representations have advanced the state-of-the-art on various commonsense NLP tasks, but we lack a concrete understanding of the capability of these models.
Low-Resource Parsing with Crosslingual Contextualized Representations
Despite advances in dependency parsing, languages with small treebanks still present challenges.
ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networks
Scientific article summarization is challenging: large, annotated corpora are not available, and the summary should ideally include the article's impacts on research community.
Ranked #1 on
Scientific Document Summarization
on CL-SciSumm
Low-resource Deep Entity Resolution with Transfer and Active Learning
Recent adaptation of deep learning methods for ER mitigates the need for dataset-specific feature engineering by constructing distributed representations of entity records.
Syntax-aware Neural Semantic Role Labeling with Supertags
We introduce a new syntax-aware model for dependency-based semantic role labeling that outperforms syntax-agnostic models for English and Spanish.
Polyglot Contextual Representations Improve Crosslingual Transfer
We introduce Rosita, a method to produce multilingual contextual word representations by training a single language model on text from multiple languages.
End-to-end Graph-based TAG Parsing with Neural Networks
We present a graph-based Tree Adjoining Grammar (TAG) parser that uses BiLSTMs, highway connections, and character-level CNNs.
Robust Multilingual Part-of-Speech Tagging via Adversarial Training
Adversarial training (AT) is a powerful regularization method for neural networks, aiming to achieve robustness to input perturbations.
Ranked #2 on
Part-Of-Speech Tagging
on UD
TAG Parsing with Neural Networks and Vector Representations of Supertags
We present supertagging-based models for Tree Adjoining Grammar parsing that use neural network architectures and dense vector representation of supertags (elementary trees) to achieve state-of-the-art performance in unlabeled and labeled attachment scores.
