Search Results for author:
Found 356 papers, 216 papers with code
Findings of the Second Workshop on Neural Machine Translation and Generation
This document describes the findings of the Second Workshop on Neural Machine Translation and Generation, held in concert with the annual conference of the Association for Computational Linguistics (ACL 2018).
Neural Factor Graph Models for Cross-lingual Morphological Tagging
Morphological analysis involves predicting the syntactic traits of a word (e. g. {POS: Noun, Case: Acc, Gender: Fem}).
Multi-Source Neural Machine Translation with Missing Data
This study focuses on the use of incomplete multilingual corpora in multi-encoder NMT and mixture of NMT experts and examines a very simple implementation where missing source translations are replaced by a special symbol <NULL>.
Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow
For tasks like code synthesis from natural language, code retrieval, and code summarization, data-driven models have shown great promise.
Guiding Neural Machine Translation with Retrieved Translation Pieces
Specifically, for an input sentence, we use a search engine to retrieve sentence pairs whose source sides are similar with the input sentence, and then collect $n$-grams that are both in the retrieved target sentences and aligned with words that match in the source sentences, which we call "translation pieces".
Handling Homographs in Neural Machine Translation
Homographs, words with different meanings but the same surface form, have long caused difficulty for machine translation systems, as it is difficult to select the correct translation based on the context.
Linguistic unit discovery from multi-modal inputs in unwritten languages: Summary of the "Speaking Rosetta" JSALT 2017 Workshop
We summarize the accomplishments of a multi-disciplinary workshop exploring the computational and scientific issues surrounding the discovery of linguistic units (subwords and words) in a language without orthography.
Controllable Invariance through Adversarial Feature Learning
Learning meaningful representations that maintain the content necessary for a particular task while filtering away detrimental variations is a problem of great interest in machine learning.
Cavs: A Vertex-centric Programming Interface for Dynamic Neural Networks
Recent deep learning (DL) models have moved beyond static network architectures to dynamic ones, handling data where the network structure changes every example, such as sequences of variable lengths, trees, and graphs.
Convolutional Neural Networks for Medical Diagnosis from Admission Notes
The hope is that the tool can be used to reduce mis-diagnosis.
Improving Neural Machine Translation through Phrase-based Forced Decoding
Compared to traditional statistical machine translation (SMT), neural machine translation (NMT) often sacrifices adequacy for the sake of fluency.
Softmax Q-Distribution Estimation for Structured Prediction: A Theoretical Interpretation for RAML
Reward augmented maximum likelihood (RAML), a simple and effective learning framework to directly optimize towards the reward function in structured prediction tasks, has led to a number of impressive empirical successes.
A Continuous Relaxation of Beam Search for End-to-end Training of Neural Sequence Models
In experiments, we show that optimizing this new training objective yields substantially better results on two sequence tasks (Named Entity Recognition and CCG Supertagging) when compared with both cross entropy trained greedy decoding and cross entropy trained beam decoding baselines.
Ranked #3 on
Motion Segmentation
on Hopkins155
Transcribing Against Time
We investigate the problem of manually correcting errors from an automatic speech transcript in a cost-sensitive fashion.
Multi-space Variational Encoder-Decoders for Semi-supervised Labeled Sequence Transduction
Labeled sequence transduction is a task of transforming one sequence into another sequence that satisfies desiderata specified by a set of labels.
Neural Lattice-to-Sequence Models for Uncertain Inputs
In this work, we extend the TreeLSTM (Tai et al., 2015) into a LatticeLSTM that is able to consume word lattices, and can be used as encoder in an attentional encoder-decoder model.
Stronger Baselines for Trustable Results in Neural Machine Translation
As a result, it is often difficult to determine whether improvements from research will carry over to systems deployed for real-world use.
An Empirical Study of Mini-Batch Creation Strategies for Neural Machine Translation
Training of neural machine translation (NMT) models usually uses mini-batches for efficiency purposes.
Neural Machine Translation via Binary Code Prediction
In this paper, we propose a new method for calculating the output layer in neural machine translation systems.
Lexicons and Minimum Risk Training for Neural Machine Translation: NAIST-CMU at WAT2016
This year, the Nara Institute of Science and Technology (NAIST)/Carnegie Mellon University (CMU) submission to the Japanese-English translation track of the 2016 Workshop on Asian Translation was based on attentional neural machine translation (NMT) models.
Neural Reranking Improves Subjective Quality of Machine Translation: NAIST at WAT2015
We further perform a detailed analysis of reasons for this increase, finding that the main contributions of the neural models lie in improvement of the grammatical correctness of the output, as opposed to improvements in lexical choice of content words.
SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translation
In this work, we examine methods for data augmentation for text-based tasks such as neural machine translation (NMT).
Multi-Source Neural Machine Translation with Data Augmentation
By using information from these multiple sources, these systems achieve large gains in accuracy.
Optimizing Segmentation Granularity for Neural Machine Translation
However, the granularity of these subword units is a hyperparameter to be tuned for each language and task, using methods such as grid search.
Towards a General-Purpose Linguistic Annotation Backend
In this extended abstract, we describe the beginnings of a new project that will attempt to ease this language documentation process through the use of natural language processing (NLP) technology.
Cross-Lingual Word Embeddings for Low-Resource Language Modeling
We investigate the use of such lexicons to improve language models when textual training data is limited to as few as a thousand sentences.
Using Morphological Knowledge in Open-Vocabulary Neural Language Models
Languages with productive morphology pose problems for language models that generate words from a fixed vocabulary.
Modelling Natural Language, Programs, and their Intersection
As a result, in the past several years there has been an increasing research interest in methods that focus on the intersection of programming and natural language, allowing users to use natural language to interact with computers in the complex ways that programs allow us to do.
How Would You Say It? Eliciting Lexically Diverse Dialogue for Supervised Semantic Parsing
Wang et al. (2015) proposed a method to build semantic parsing datasets by generating canonical utterances using a grammar and having crowdworkers paraphrase them into natural wording.
Overview of the 4th Workshop on Asian Translation
For the WAT2017, 12 institutions participated in the shared tasks.
Overview of the 3rd Workshop on Asian Translation
For the WAT2016, 15 institutions participated in the shared tasks.
Lightly Supervised Quality Estimation
Evaluating the quality of output from language processing systems such as machine translation or speech recognition is an essential step in ensuring that they are sufficient for practical use.
On Meaning-Preserving Adversarial Perturbations for Sequence-to-Sequence Models
Adversarial examples have been shown to be an effective way of assessing the robustness of neural sequence-to-sequence (seq2seq) models, by applying perturbations to the input of a model leading to large degradation in performance.
An Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation
In this work, we propose a method for neural dialogue response generation that allows not only generating semantically reasonable responses according to the dialogue history, but also explicitly controlling the sentiment of the response via sentiment labels.
Semantic Parsing of Ambiguous Input through Paraphrasing and Verification
We propose a new method for semantic parsing of ambiguous and ungrammatical input, such as search queries.
Segmentation for Efficient Supervised Language Annotation with an Explicit Cost-Utility Tradeoff
In this paper, we study the problem of manually correcting automatic annotations of natural language in as efficient a manner as possible.
Collection of a Simultaneous Translation Corpus for Comparative Analysis
This makes it possible to compare translation data with simultaneous interpretation data.
Language Resource Addition: Dictionary or Corpus?
The experimental results showed that the annotated sentence addition to the training corpus is better than the entries addition to the dictionary.
Towards Multilingual Conversations in the Medical Domain: Development of Multilingual Medical Data and A Network-based ASR System
This paper outlines the recent development on multilingual medical data and multilingual speech recognition system for network-based speech-to-speech translation in the medical domain.
The ARIEL-CMU Systems for LoReHLT18
This paper describes the ARIEL-CMU submissions to the Low Resource Human Language Technologies (LoReHLT) 2018 evaluations for the tasks Machine Translation (MT), Entity Discovery and Linking (EDL), and detection of Situation Frames in Text and Speech (SF Text and Speech).
Attention-Passing Models for Robust and Data-Efficient End-to-End Speech Translation
Speech translation has traditionally been approached through cascaded models consisting of a speech recognizer trained on a corpus of transcribed speech, and a machine translation system trained on parallel texts.
Target Conditioned Sampling: Optimizing Data Selection for Multilingual Neural Machine Translation
To improve low-resource Neural Machine Translation (NMT) with multilingual corpora, training on the most related high-resource language only is often more effective than using all data available (Neubig and Hu, 2018).
Self-Attentional Models for Lattice Inputs
Lattices are an efficient and effective method to encode ambiguity of upstream systems in natural language processing tasks, for example to compactly capture multiple speech recognition hypotheses, or to represent multiple linguistic analyses.
Learning to Describe Unknown Phrases with Local and Global Contexts
When reading a text, it is common to become stuck on unfamiliar words and phrases, such as polysemous words with novel senses, rarely used idioms, internet slang, or emerging entities.
Optimizing Computer-Assisted Transcription Quality with Iterative User Interfaces
Our goal is to improve the human transcription quality via appropriate user interface design.
Generalized Data Augmentation for Low-Resource Translation
Translation to or from low-resource languages LRLs poses challenges for machine translation in terms of both adequacy and fluency.
Beyond BLEU:Training Neural Machine Translation with Semantic Similarity
While most neural machine translation (NMT)systems are still trained using maximum likelihood estimation, recent work has demonstrated that optimizing systems to directly improve evaluation metrics such as BLEU can significantly improve final translation accuracy.
Reranking for Neural Semantic Parsing
Semantic parsing considers the task of transducing natural language (NL) utterances into machine executable meaning representations (MRs).
Ranked #4 on
Code Generation
on Django
Mitigating Noisy Inputs for Question Answering
We investigate and mitigate the effects of noise from Automatic Speech Recognition systems on two factoid Question Answering (QA) tasks.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+6
Latent Relation Language Models
In this paper, we propose Latent Relation Language Models (LRLMs), a class of language models that parameterizes the joint distribution over the words in a document and the entities that occur therein via knowledge graph relations.
Contextualized Representations for Low-resource Utterance Tagging
Utterance-level analysis of the speaker{'}s intentions and emotions is a core task in conversational understanding.
Findings of the Third Workshop on Neural Generation and Translation
This document describes the findings of the Third Workshop on Neural Generation and Translation, held in concert with the annual conference of the Empirical Methods in Natural Language Processing (EMNLP 2019).
Comparing Top-Down and Bottom-Up Neural Generative Dependency Models
Recurrent neural network grammars generate sentences using phrase-structure syntax and perform very well on both parsing and language modeling.
Understanding Knowledge Distillation in Non-autoregressive Machine Translation
We find that knowledge distillation can reduce the complexity of data sets and help NAT to model the variations in the output data.
AlloVera: A Multilingual Allophone Database
While phonemic representations are language specific, phonetic representations (stated in terms of (allo)phones) are much closer to a universal (language-independent) transcription.
A Summary of the First Workshop on Language Technology for Language Documentation and Revitalization
Despite recent advances in natural language processing and other language technology, the application of such technology to language documentation and conservation has been limited.
Weight Poisoning Attacks on Pretrained Models
Recently, NLP has seen a surge in the usage of large pre-trained models.
Findings of the Fourth Workshop on Neural Generation and Translation
We describe the finding of the Fourth Workshop on Neural Generation and Translation, held in concert with the annual conference of the Association for Computational Linguistics (ACL 2020).
Transliteration for Cross-Lingual Morphological Inflection
Cross-lingual transfer between typologically related languages has been proven successful for the task of morphological inflection.
TICO-19: the Translation Initiative for Covid-19
Further, the team is converting the test and development data into translation memories (TMXs) that can be used by localizers from and to any of the languages.
Improving Target-side Lexical Transfer in Multilingual Neural Machine Translation
To improve the performance of Neural Machine Translation~(NMT) for low-resource languages~(LRL), one effective strategy is to leverage parallel data from a related high-resource language~(HRL).
Explicit Alignment Objectives for Multilingual Bidirectional Encoders
Pre-trained cross-lingual encoders such as mBERT (Devlin et al., 2019) and XLMR (Conneau et al., 2020) have proven to be impressively effective at enabling transfer-learning of NLP systems from high-resource languages to low-resource languages.
Reducing Confusion in Active Learning for Part-Of-Speech Tagging
Active learning (AL) uses a data selection algorithm to select useful training samples to minimize annotation cost.
Decoding and Diversity in Machine Translation
This makes human-level BLEU a misleading benchmark in that modern MT systems cannot approach human-level BLEU while simultaneously maintaining human-level translation diversity.
In-IDE Code Generation from Natural Language: Promise and Challenges
A great part of software development involves conceptualizing or communicating the underlying procedures and logic that needs to be expressed in programs.
Code Generation
Data Visualization
Software Engineering
Phoneme Recognition through Fine Tuning of Phonetic Representations: a Case Study on Luhya Language Varieties
Models pre-trained on multiple languages have shown significant promise for improving speech recognition, particularly for low-resource languages.
Data Augmentation for Sign Language Gloss Translation
Sign language translation (SLT) is often decomposed into video-to-gloss recognition and gloss-to-text translation, where a gloss is a sequence of transcribed spoken-language words in the order in which they are signed.
Data Augmentation
Low-Resource Neural Machine Translation
+3
Compositional Generalization for Neural Semantic Parsing via Span-level Supervised Attention
We describe a span-level supervised attention loss that improves compositional generalization in semantic parsers.
Phrase-level Active Learning for Neural Machine Translation
Neural machine translation (NMT) is sensitive to domain shift.
Few-shot Language Coordination by Modeling Theory of Mind
Positive results from our experiments hint at the importance of explicitly modeling communication as a socio-pragmatic progress.
Endangered Languages meet Modern NLP
This tutorial will focus on NLP for endangered languages documentation and revitalization.
Automatic Interlinear Glossing for Under-Resourced Languages Leveraging Translations
Interlinear Glossed Text (IGT) is a widely used format for encoding linguistic information in language documentation projects and scholarly papers.
When Does Translation Require Context? A Data-driven, Multilingual Exploration
Although proper handling of discourse significantly contributes to the quality of machine translation (MT), these improvements are not adequately measured in common translation quality metrics.
Procedures as Programs: Hierarchical Control of Situated Agents through Natural Language
When humans conceive how to perform a particular task, they do so hierarchically: splitting higher-level tasks into smaller sub-tasks.
Learning to Superoptimize Real-world Programs
We also report that SILO's rate of superoptimization on our test set is over five times that of a standard policy gradient approach and a model pre-trained on compiler optimization demonstration.
Capturing Structural Locality in Non-parametric Language Models
Structural locality is a ubiquitous feature of real-world datasets, wherein data points are organized into local hierarchies.
Symmetric Machine Theory of Mind
Theory of mind (ToM), the ability to understand others' thoughts and desires, is a cornerstone of human intelligence.
Breaking Down Multilingual Machine Translation
While multilingual training is now an essential ingredient in machine translation (MT) systems, recent work has demonstrated that it has different effects in different multilingual settings, such as many-to-one, one-to-many, and many-to-many learning.
On The Ingredients of an Effective Zero-shot Semantic Parser
Semantic parsers map natural language utterances into meaning representations (e. g., programs).
Project MAIA: Multilingual AI Agent Assistant
This paper presents the Multilingual Artificial Intelligence Agent Assistant (MAIA), a project led by Unbabel with the collaboration of CMU, INESC-ID and IT Lisbon.
When is Wall a Pared and when a Muro?: Extracting Rules Governing Lexical Selection
Learning fine-grained distinctions between vocabulary items is a key challenge in learning a new language.
Findings of the WMT 2020 Shared Task on Machine Translation Robustness
We report the findings of the second edition of the shared task on improving robustness in Machine Translation (MT).
Findings of the AmericasNLP 2021 Shared Task on Open Machine Translation for Indigenous Languages of the Americas
This paper presents the results of the 2021 Shared Task on Open Machine Translation for Indigenous Languages of the Americas.
DEEP: DEnoising Entity Pre-training for Neural Machine Translation
It has been shown that machine translation models usually generate poor translations for named entities that are infrequent in the training corpus.
Measuring Density and Similarity of Task Relevant Information in Neural Representations
Neural models achieve state-of-the-art performance due to their ability to extract salient features useful to downstream tasks.
BLISS in Non-Isometric Embedding Spaces
We then propose Bilingual Lexicon Induction with Semi-Supervision (BLISS) --- a novel semi-supervised approach that relaxes the isometric assumption while leveraging both limited aligned bilingual lexicons and a larger set of unaligned word embeddings, as well as a novel hubness filtering technique.
Regularizing Trajectories to Mitigate Catastrophic Forgetting
Regularization-based continual learning approaches generally prevent catastrophic forgetting by augmenting the training loss with an auxiliary objective.
DataLab: A Platform for Data Analysis and Intervention
Despite data's crucial role in machine learning, most existing tools and research tend to focus on systems on top of existing data rather than how to interpret and manipulate data.
AUTOLEX: An Automatic Framework for Linguistic Exploration
Each language has its own complex systems of word, phrase, and sentence construction, the guiding principles of which are often summarized in grammar descriptions for the consumption of linguists or language learners.
CMU’s IWSLT 2022 Dialect Speech Translation System
We use additional paired Modern Standard Arabic data (MSA) to directly improve the speech recognition (ASR) and machine translation (MT) components of our cascaded systems.
Teacher Perception of Automatically Extracted Grammar Concepts for L2 Language Learning
This process is challenging because i) it requires that such experts be accessible and have the necessary resources, and ii) even if there are such experts, describing all the intricacies of a language is time-consuming and prone to omission.
KGxBoard: Explainable and Interactive Leaderboard for Evaluation of Knowledge Graph Completion Models
Knowledge Graphs (KGs) store information in the form of (head, predicate, tail)-triples.
Understanding and Improving Zero-shot Multi-hop Reasoning in Generative Question Answering
In sum, these results demonstrate that multi-hop reasoning does not emerge naturally in generative QA models, but can be encouraged by advances in training or modeling techniques.
CTC Alignments Improve Autoregressive Translation
Connectionist Temporal Classification (CTC) is a widely used approach for automatic speech recognition (ASR) that performs conditionally independent monotonic alignment.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
A Multi-dimensional Evaluation of Tokenizer-free Multilingual Pretrained Models
Recent work on tokenizer-free multilingual pretrained models show promising results in improving cross-lingual transfer and reducing engineering overhead (Clark et al., 2022; Xue et al., 2022).
DiffusER: Discrete Diffusion via Edit-based Reconstruction
In text generation, models that generate text from scratch one token at a time are currently the dominant paradigm.
Searching for Effective Multilingual Fine-Tuning Methods: A Case Study in Summarization
Recently, a large number of tuning strategies have been proposed to adapt pre-trained language models to downstream tasks.
User-Centric Evaluation of OCR Systems for Kwak'wala
There has been recent interest in improving optical character recognition (OCR) for endangered languages, particularly because a large number of documents and books in these languages are not in machine-readable formats.
Optical Character Recognition
Optical Character Recognition (OCR)
Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generation
Many recent advances in natural language generation have been fueled by training large language models on internet-scale data.
EXCALIBUR: Encouraging and Evaluating Embodied Exploration
Humans constantly explore and learn about their environment out of curiosity, gather information, and update their models of the world.
Solving NLP Problems through Human-System Collaboration: A Discussion-based Approach
Humans work together to solve common problems by having discussions, explaining, and agreeing or disagreeing with each other.
GlobalBench: A Benchmark for Global Progress in Natural Language Processing
Despite the major advances in NLP, significant disparities in NLP system performance across languages still exist.
Multi-lingual and Multi-cultural Figurative Language Understanding
Figurative language permeates human communication, but at the same time is relatively understudied in NLP.
Syntax and Semantics Meet in the "Middle": Probing the Syntax-Semantics Interface of LMs Through Agentivity
Recent advances in large language models have prompted researchers to examine their abilities across a variety of linguistic tasks, but little has been done to investigate how models handle the interactions in meaning across words and larger syntactic forms -- i. e. phenomena at the intersection of syntax and semantics.
Neural Machine Translation for the Indigenous Languages of the Americas: An Introduction
Neural models have drastically advanced state of the art for machine translation (MT) between high-resource languages.
Improving Factuality of Abstractive Summarization via Contrastive Reward Learning
Modern abstractive summarization models often generate summaries that contain hallucinated or contradictory information.
The Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation
Automatic evaluation of machine translation (MT) is a critical tool driving the rapid iterative development of MT systems.
Teacher Perception of Automatically Extracted Grammar Concepts for L2 Language Learning
This is challenging because i) it requires that such experts be accessible and have the necessary resources, and ii) describing all the intricacies of a language is time-consuming and prone to omission.
DeMuX: Data-efficient Multilingual Learning
In this paper, we introduce DEMUX, a framework that prescribes the exact data-points to label from vast amounts of unlabelled multilingual data, having unknown degrees of overlap with the target set.
Program-Aided Reasoners (better) Know What They Know
Our analysis uncovers that prompting styles that produce lesser diversity in generations also have more calibrated results, and thus we also experiment with inducing lower generation diversity using temperature scaling and find that for certain temperatures, PAL is not only more accurate but is also more calibrated than COT.
Fine-grained Hallucination Detection and Editing for Language Models
On our benchmark, our automatic and human evaluations show that FAVA significantly outperforms ChatGPT and GPT-4 on fine-grained hallucination detection, and edits suggested by FAVA improve the factuality of LM-generated text.
Instruction-tuned Language Models are Better Knowledge Learners
The standard recipe for doing so involves continued pre-training on new documents followed by instruction-tuning on question-answer (QA) pairs.
What Is Missing in Multilingual Visual Reasoning and How to Fix It
NLP models today strive for supporting multiple languages and modalities, improving accessibility for diverse users.
GlossLM: Multilingual Pretraining for Low-Resource Interlinear Glossing
A key aspect of language documentation is the creation of annotated text in a format such as interlinear glossed text (IGT), which captures fine-grained morphosyntactic analyses in a morpheme-by-morpheme format.
Wav2Gloss: Generating Interlinear Glossed Text from Speech
Thousands of the world's languages are in danger of extinction--a tremendous threat to cultural identities and human language diversity.
What Are Tools Anyway? A Survey from the Language Model Perspective
Language models (LMs) are powerful yet mostly for text generation tasks.
An Incomplete Loop: Deductive, Inductive, and Abductive Learning in Large Language Models
Modern language models (LMs) can learn to perform new tasks in different ways: in instruction following, the target task is described explicitly in natural language; in few-shot prompting, the task is specified implicitly with a small number of examples; in instruction inference, LMs are presented with in-context examples and are then prompted to generate a natural language task description before making predictions.
VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?
Multimodal Large Language models (MLLMs) have shown promise in web-related tasks, but evaluating their performance in the web domain remains a challenge due to the lack of comprehensive benchmarks.
Neural Machine Translation and Sequence-to-sequence Models: A Tutorial
This tutorial introduces a new and powerful set of techniques variously called "neural machine translation" or "neural sequence-to-sequence models".
Domain Differential Adaptation for Neural Machine Translation
We then use these learned domain differentials to adapt models for the target task accordingly.
Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations
Through our evaluation, we observe that for a linear bag-of-words model, participants with access to the feature coefficients during training are able to cause a larger reduction in model confidence in the testing phase when compared to the no-explanation control.
AANG: Automating Auxiliary Learning
Auxiliary objectives, supplementary learning signals that are introduced to help aid learning on data-starved or highly complex end-tasks, are commonplace in machine learning.
Contextual Encoding for Translation Quality Estimation
In this paper, propose a method to effectively encode the local and global contextual information for each target word using a three-part neural network approach.
Automatic Extraction of Rules Governing Morphological Agreement
Using cross-lingual transfer, even with no expert annotations in the language of interest, our framework extracts a grammatical specification which is nearly equivalent to those created with large amounts of gold-standard annotated data.
Dependency Induction Through the Lens of Visual Perception
Our experiments find that concreteness is a strong indicator for learning dependency grammars, improving the direct attachment score (DAS) by over 50\% as compared to state-of-the-art models trained on pure text.
T5Score: Discriminative Fine-tuning of Generative Evaluation Metrics
Both have their advantages; discriminative metrics are able to directly optimize for the problem of distinguishing between good and bad outputs, while generative metrics can be trained using abundant raw text.
Crossing the Threshold: Idiomatic Machine Translation through Retrieval Augmentation and Loss Weighting
Idioms are common in everyday language, but often pose a challenge to translators because their meanings do not follow from the meanings of their parts.
Divergences between Language Models and Human Brains
In this work, we systematically explore the divergences between human and machine language processing by examining the differences between LM representations and human brain responses to language as measured by Magnetoencephalography (MEG) across two datasets in which subjects read and listened to narrative stories.
A Set of Recommendations for Assessing Human-Machine Parity in Language Translation
The quality of machine translation has increased remarkably over the past years, to the degree that it was found to be indistinguishable from professional human translation in a number of empirical investigations.
Evaluating Explanations: How much do explanations from the teacher aid students?
While many methods purport to explain predictions by highlighting salient features, what aims these explanations serve and how they ought to be evaluated often go unstated.
When is Wall a Pared and when a Muro? -- Extracting Rules Governing Lexical Selection
Learning fine-grained distinctions between vocabulary items is a key challenge in learning a new language.
Self-Attentional Acoustic Models
Self-attention is a method of encoding sequences of vectors by relating these vectors to each-other based on pairwise similarities.
Towards Zero-resource Cross-lingual Entity Linking
Cross-lingual entity linking (XEL) grounds named entities in a source language to an English Knowledge Base (KB), such as Wikipedia.
Optimizing Data Usage via Differentiable Rewards
To acquire a new skill, humans learn better and faster if a tutor, based on their current knowledge level, informs them of how much attention they should pay to particular content or practice problems.
Are Representations Built from the Ground Up? An Empirical Examination of Local Composition in Language Models
We find that the representation of a parent phrase can be predicted with some accuracy given an affine transformation of its children.
Multi-Dimensional Evaluation of Text Summarization with In-Context Learning
Most frameworks that perform such multi-dimensional evaluation require training on large manually or synthetically generated datasets.
ChatGPT MT: Competitive for High- (but not Low-) Resource Languages
Without published experimental evidence on the matter, it is difficult for speakers of the world's diverse languages to know how and whether they can use LLMs for their languages.
Multitask Learning Can Improve Worst-Group Outcomes
We primarily consider the standard setting of fine-tuning a pre-trained model, where, following recent work \citep{gururangan2020don, dery2023aang}, we multitask the end task with the pre-training objective constructed from the end task data itself.
Automatic Estimation of Simultaneous Interpreter Performance
Simultaneous interpretation, translation of the spoken word in real-time, is both highly challenging and physically demanding.
Attentive Interaction Model: Modeling Changes in View in Argumentation
We present a neural architecture for modeling argumentative dialogue that explicitly models the interplay between an Opinion Holder's (OH's) reasoning and a challenger's argument, with the goal of predicting if the argument successfully changes the OH's view.
Handling Syntactic Divergence in Low-resource Machine Translation
Despite impressive empirical successes of neural machine translation (NMT) on standard benchmarks, limited parallel data impedes the application of NMT models to many language pairs.
Practical Comparable Data Collection for Low-Resource Languages via Images
We propose a method of curating high-quality comparable training data for low-resource languages with monolingual annotators.
Towards More Fine-grained and Reliable NLP Performance Prediction
We perform an analysis of four types of NLP tasks, and both demonstrate the feasibility of fine-grained performance prediction and the necessity to perform reliability analysis for performance prediction methods in the future.
AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages
Continued pretraining offers improvements, with an average accuracy of 44. 05%.
Systematic Inequalities in Language Technology Performance across the World's Languages
Natural language processing (NLP) systems have become a central technology in communication, education, medicine, artificial intelligence, and many other domains of research and development.
Learning Relation Entailment with Structured and Textual Information
We propose several methods that incorporate both structured and textual information to represent relations for this task.
Systematic Inequalities in Language Technology Performance across the World’s Languages
Natural language processing (NLP) systems have become a central technology in communication, education, medicine, artificial intelligence, and many other domains of research and development.
He Said, She Said: Style Transfer for Shifting the Perspective of Dialogues
As a sample application, we demonstrate that applying perspective shifting to a dialogue summarization dataset (SAMSum) substantially improves the zero-shot performance of extractive news summarization models on this data.
Lost in Interpretation: Predicting Untranslated Terminology in Simultaneous Interpretation
Simultaneous interpretation, the translation of speech from one language to another in real-time, is an inherently difficult and strenuous task.
Dynamic Data Selection and Weighting for Iterative Back-Translation
Back-translation has proven to be an effective method to utilize monolingual data in neural machine translation (NMT), and iteratively conducting back-translation can further improve the model performance.
Adapting Word Embeddings to New Languages with Morphological and Phonological Subword Representations
Much work in Natural Language Processing (NLP) has been for resource-rich languages, making generalization to new, less-resourced languages challenging.
Unsupervised Domain Adaptation for Neural Machine Translation with Domain-Aware Feature Embeddings
The recent success of neural machine translation models relies on the availability of high quality, in-domain data.
Evaluating the Morphosyntactic Well-formedness of Generated Texts
Text generation systems are ubiquitous in natural language processing applications.
Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative
In most settings of practical concern, machine learning practitioners know in advance what end-task they wish to boost with auxiliary tasks.
Do LLMs exhibit human-like response biases? A case study in survey design
As large language models (LLMs) become more capable, there is growing excitement about the possibility of using LLMs as proxies for humans in real-world tasks where subjective labels are desired, such as in surveys and opinion polling.
On Learning Text Style Transfer with Direct Rewards
In most cases, the lack of parallel corpora makes it impossible to directly train supervised models for the text style transfer task.
AfroMT: Pretraining Strategies and Reproducible Benchmarks for Translation of 8 African Languages
Reproducible benchmarks are crucial in driving progress of machine translation research.
CharManteau: Character Embedding Models For Portmanteau Creation
Portmanteaus are a word formation phenomenon where two words are combined to form a new word.
A Bilingual Generative Transformer for Semantic Sentence Embedding
Semantic sentence embedding models encode natural language sentences into vectors, such that closeness in embedding space indicates closeness in the semantics between the sentences.
An image speaks a thousand words, but can everyone listen? On translating images for cultural relevance
First, we build three pipelines comprising state-of-the-art generative models to do the task.
Zero-shot Neural Transfer for Cross-lingual Entity Linking
To address this problem, we investigate zero-shot cross-lingual entity linking, in which we assume no bilingual lexical resources are available in the source low-resource language.
Merging Weak and Active Supervision for Semantic Parsing
Experiments on WikiTableQuestions with human annotators show that our method can improve the performance with only 100 active queries, especially for weakly-supervised parsers learnt from a cold start.
Building African Voices
This paper focuses on speech synthesis for low-resourced African languages, from corpus creation to sharing and deploying the Text-to-Speech (TTS) systems.
CMULAB: An Open-Source Framework for Training and Deployment of Natural Language Processing Models
Effectively using Natural Language Processing (NLP) tools in under-resourced languages requires a thorough understanding of the language itself, familiarity with the latest models and training methodologies, and technical expertise to deploy these models.
Should All Cross-Lingual Embeddings Speak English?
Most of recent work in cross-lingual word embeddings is severely Anglocentric.
Efficient Test Time Adapter Ensembling for Low-resource Language Varieties
Adapters are light-weight modules that allow parameter-efficient fine-tuning of pretrained models.
Show Me More Details: Discovering Hierarchies of Procedures from Semi-structured Web Data
To this end, we develop a simple and efficient method that links steps (e. g., "purchase a camera") in an article to other articles with similar goals (e. g., "how to choose a camera"), recursively constructing the KB.
Quality-Aware Decoding for Neural Machine Translation
Despite the progress in machine translation quality estimation and evaluation in the last years, decoding in neural machine translation (NMT) is mostly oblivious to this and centers around finding the most probable translation according to the model (MAP decoding), approximated with beam search.
Computational Language Acquisition with Theory of Mind
We also find some evidence that increasing task difficulty in the training process results in more fluent and precise utterances in evaluation.
Learning Character-level Compositionality with Visual Features
Previous work has modeled the compositionality of words by creating character-level models of meaning, reducing problems of sparsity for rare words.
Bilingual Lexicon Induction with Semi-supervision in Non-Isometric Embedding Spaces
We then propose Bilingual Lexicon Induction with Semi-Supervision (BLISS) --- a semi-supervised approach that relaxes the isometric assumption while leveraging both limited aligned bilingual lexicons and a larger set of unaligned word embeddings, as well as a novel hubness filtering technique.
