Search Results for author:
Found 85 papers, 30 papers with code
The University of Maryland, College Park Submission to Large-Scale Multilingual Shared Task at WMT 2021
This paper describes the system submitted to Large-Scale Multilingual Shared Task (Small Task #2) at WMT 2021.
The University of Maryland’s Submissions to the WMT20 Chat Translation Task: Searching for More Data to Adapt Discourse-Aware Neural Machine Translation
This paper describes the University of Maryland’s submissions to the WMT20 Shared Task on Chat Translation.
Constrained Regeneration for Cross-Lingual Query-Focused Extractive Summarization
Query-focused summaries of foreign-language, retrieved documents can help a user understand whether a document is actually relevant to the query term.
Models and Tasks for Human-Centered Machine Translation
In this talk, I will describe current research directions in my group that aim to make machine translation (MT) more human-centered.
Machine Translation Believability
Successful Machine Translation (MT) deployment requires understanding not only the intrinsic qualities of MT output, such as fluency and adequacy, but also user perceptions.
The UMD Machine Translation Systems at IWSLT 2016: English-to-French Translation of Speech Transcripts
We describe the University of Maryland machine translation system submitted to the IWSLT 2016 Microsoft Speech Language Translation (MSLT) English-French task.
Automatic Input Rewriting Improves Translation with Large Language Models
We show that text simplification is the most effective MT-agnostic rewrite strategy and that it can be improved further when using quality estimation to assess translatability.
Findings of the IWSLT 2024 Evaluation Campaign
This paper reports on the shared tasks organized by the 21st IWSLT Conference.
SpeechQE: Estimating the Quality of Direct Speech Translation
Recent advances in automatic quality estimation for machine translation have exclusively focused on written language, leaving the speech modality underexplored.
Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?
We propose VocADT, a novel method for vocabulary adaptation using adapter modules that are trained to learn the optimal linear combination of existing embeddings while keeping the model's weights fixed.
Plausibly Problematic Questions in Multiple-Choice Benchmarks for Commonsense Reasoning
Questions involving commonsense reasoning about everyday situations often admit many $\textit{possible}$ or $\textit{plausible}$ answers.
The Prompt Report: A Systematic Survey of Prompting Techniques
Generative Artificial Intelligence (GenAI) systems are increasingly being deployed across diverse industries and research domains.
How Multilingual Are Large Language Models Fine-Tuned for Translation?
To address these questions, we conduct an extensive empirical evaluation of the translation quality of the TOWER family of language models (Alves et al., 2024) on 132 translation tasks from the multi-parallel FLORES-200 data.
Keep It Private: Unsupervised Privatization of Online Text
Authorship obfuscation techniques hold the promise of helping people protect their privacy in online communications by automatically rewriting text to hide the identity of the original author.
How often are errors in natural language reasoning due to paraphrastic variability?
We propose a metric for evaluating the paraphrastic consistency of natural language reasoning models based on the probability of a model achieving the same correctness on two paraphrases of the same problem.
Guiding Large Language Models to Post-Edit Machine Translation with Error Annotations
Machine Translation (MT) remains one of the last NLP tasks where large language models (LLMs) have not yet replaced dedicated supervised systems.
XLAVS-R: Cross-Lingual Audio-Visual Speech Representation Learning for Noise-Robust Speech Perception
It is designed to maximize the benefits of limited multilingual AV pre-training data, by building on top of audio-only multilingual pre-training and simplifying existing pre-training schemes.
Do Text Simplification Systems Preserve Meaning? A Human Evaluation via Reading Comprehension
With this framework, we conduct a thorough human evaluation of texts by humans and by nine automatic systems.
Explaining with Contrastive Phrasal Highlighting: A Case Study in Assisting Humans to Detect Translation Differences
Explainable NLP techniques primarily explain by answering "Which tokens in the input are responsible for this prediction?''.
Bridging Background Knowledge Gaps in Translation with Automatic Explicitation
Translations help people understand content written in another language.
Improving Word Sense Disambiguation in Neural Machine Translation with Salient Document Context
Lexical ambiguity is a challenging and pervasive problem in machine translation (\mt).
AfriMTE and AfriCOMET: Enhancing COMET to Embrace Under-resourced African Languages
Despite the recent progress on scaling multilingual machine translation (MT) to several under-resourced African languages, accurately measuring this progress remains challenging, since evaluation is often performed on n-gram matching metrics such as BLEU, which typically show a weaker correlation with human judgments.
Physician Detection of Clinical Harm in Machine Translation: Quality Estimation Aids in Reliance and Backtranslation Identifies Critical Errors
A major challenge in the practical use of Machine Translation (MT) is that users lack guidance to make informed decisions about when to rely on outputs.
Towards Conceptualization of "Fair Explanation": Disparate Impacts of anti-Asian Hate Speech Explanations on Content Moderators
We apply this method in the context of content moderation of potential hate speech, and its differential impact on Asian vs. non-Asian proxy moderators, across explanation approaches (saliency map and counterfactual explanation).
Controlling Pre-trained Language Models for Grade-Specific Text Simplification
Based on these insights, we introduce a simple method that predicts the edit operations required for simplifying a text for a specific grade level on an instance-per-instance basis.
What Else Do I Need to Know? The Effect of Background Information on Users' Reliance on QA Systems
In this work, we study how users interact with QA systems in the absence of sufficient information to assess their predictions.
Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection
Neural sequence generation models are known to "hallucinate", by producing outputs that are unrelated to the source text.
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.
Facilitating Global Team Meetings Between Language-Based Subgroups: When and How Can Machine Translation Help?
We manipulated the exchange of subgroup conversation logs prior to team meetings: with MT-mediated exchanges versus without.
Controlling Translation Formality Using Pre-trained Multilingual Language Models
This paper describes the University of Maryland's submission to the Special Task on Formality Control for Spoken Language Translation at \iwslt, which evaluates translation from English into 6 languages with diverse grammatical formality markers.
An Imitation Learning Curriculum for Text Editing with Non-Autoregressive Models
We propose a framework for training non-autoregressive sequence-to-sequence models for editing tasks, where the original input sequence is iteratively edited to produce the output.
Can Synthetic Translations Improve Bitext Quality?
Synthetic translations have been used for a wide range of NLP tasks primarily as a means of data augmentation.
Evaluating the Evaluation Metrics for Style Transfer: A Case Study in Multilingual Formality Transfer
While the field of style transfer (ST) has been growing rapidly, it has been hampered by a lack of standardized practices for automatic evaluation.
Rule-based Morphological Inflection Improves Neural Terminology Translation
Current approaches to incorporating terminology constraints in machine translation (MT) typically assume that the constraint terms are provided in their correct morphological forms.
A Review of Human Evaluation for Style Transfer
However, in style transfer papers, we find that protocols for human evaluations are often underspecified and not standardized, which hampers the reproducibility of research in this field and progress toward better human and automatic evaluation methods.
Beyond Noise: Mitigating the Impact of Fine-grained Semantic Divergences on Neural Machine Translation
While it has been shown that Neural Machine Translation (NMT) is highly sensitive to noisy parallel training samples, prior work treats all types of mismatches between source and target as noise.
How Does Distilled Data Complexity Impact the Quality and Confidence of Non-Autoregressive Machine Translation?
While non-autoregressive (NAR) models are showing great promise for machine translation, their use is limited by their dependence on knowledge distillation from autoregressive models.
EDITOR: an Edit-Based Transformer with Repositioning for Neural Machine Translation with Soft Lexical Constraints
We introduce an Edit-Based Transformer with Repositioning (EDITOR), which makes sequence generation flexible by seamlessly allowing users to specify preferences in output lexical choice.
Incorporating Terminology Constraints in Automatic Post-Editing
In this paper, we present both autoregressive and non-autoregressive models for lexically constrained APE, demonstrating that our approach enables preservation of 95% of the terminologies and also improves translation quality on English-German benchmarks.
Dual Reconstruction: a Unifying Objective for Semi-Supervised Neural Machine Translation
While Iterative Back-Translation and Dual Learning effectively incorporate monolingual training data in neural machine translation, they use different objectives and heuristic gradient approximation strategies, and have not been extensively compared.
Detecting Fine-Grained Cross-Lingual Semantic Divergences without Supervision by Learning to Rank
Detecting fine-grained differences in content conveyed in different languages matters for cross-lingual NLP and multilingual corpora analysis, but it is a challenging machine learning problem since annotation is expensive and hard to scale.
Multitask Models for Controlling the Complexity of Neural Machine Translation
We introduce a machine translation task where the output is aimed at audiences of different levels of target language proficiency.
An Evaluation of Subword Segmentation Strategies for Neural Machine Translation of Morphologically Rich Languages
Byte-Pair Encoding (BPE) (Sennrich et al., 2016) has become a standard pre-processing step when building neural machine translation systems.
Flexible Non-Autoregressive Neural Machine Translation via Repositioning Edit Operations
We introduce an iterative text refinement model to reduce the decoding space of non-autoregressive models by disentangling the token prediction and relative position prediction.
Evaluating a Bi-LSTM Model for Metaphor Detection in TOEFL Essays
However, the Bi-LSTM models lag behind the best performing systems in the shared task.
Generating Diverse Translations via Weighted Fine-tuning and Hypotheses Filtering for the Duolingo STAPLE Task
This paper describes the University of Maryland{'}s submission to the Duolingo Shared Task on Simultaneous Translation And Paraphrase for Language Education (STAPLE).
Controlling Neural Machine Translation Formality with Synthetic Supervision
This work aims to produce translations that convey source language content at a formality level that is appropriate for a particular audience.
Controlling Text Complexity in Neural Machine Translation
This work introduces a machine translation task where the output is aimed at audiences of different levels of target language proficiency.
Weakly Supervised Cross-lingual Semantic Relation Classification via Knowledge Distillation
Our classifier relies on a novel attention-based distillation approach to account for translation ambiguity when transferring knowledge from English to cross-lingual settings.
The University of Maryland's Kazakh-English Neural Machine Translation System at WMT19
This paper describes the University of Maryland{'}s submission to the WMT 2019 Kazakh-English news translation task.
Curriculum Learning for Domain Adaptation in Neural Machine Translation
We introduce a curriculum learning approach to adapt generic neural machine translation models to a specific domain.
Differentiable Sampling with Flexible Reference Word Order for Neural Machine Translation
Despite some empirical success at correcting exposure bias in machine translation, scheduled sampling algorithms suffer from a major drawback: they incorrectly assume that words in the reference translations and in sampled sequences are aligned at each time step.
An Empirical Exploration of Curriculum Learning for Neural Machine Translation
Machine translation systems based on deep neural networks are expensive to train.
Bi-Directional Differentiable Input Reconstruction for Low-Resource Neural Machine Translation
We aim to better exploit the limited amounts of parallel text available in low-resource settings by introducing a differentiable reconstruction loss for neural machine translation (NMT).
Low Resource Neural Machine Translation
Low-Resource Neural Machine Translation
+2
The University of Maryland's Chinese-English Neural Machine Translation Systems at WMT18
This paper describes the University of Maryland{'}s submission to the WMT 2018 Chinese↔English news translation tasks.
Multi-Task Neural Models for Translating Between Styles Within and Across Languages
Generating natural language requires conveying content in an appropriate style.
UMD at SemEval-2018 Task 10: Can Word Embeddings Capture Discriminative Attributes?
We describe the University of Maryland{'}s submission to SemEval-018 Task 10, {``}Capturing Discriminative Attributes{''}: given word triples (w1, w2, d), the goal is to determine whether d is a discriminating attribute belonging to w1 but not w2.
Bi-Directional Neural Machine Translation with Synthetic Parallel Data
Despite impressive progress in high-resource settings, Neural Machine Translation (NMT) still struggles in low-resource and out-of-domain scenarios, often failing to match the quality of phrase-based translation.
Robust Cross-lingual Hypernymy Detection using Dependency Context
We propose BISPARSE-DEP, a family of unsupervised approaches for cross-lingual hypernymy detection, which learns sparse, bilingual word embeddings based on dependency contexts.
Identifying Semantic Divergences in Parallel Text without Annotations
Recognizing that even correct translations are not always semantically equivalent, we automatically detect meaning divergences in parallel sentence pairs with a deep neural model of bilingual semantic similarity which can be trained for any parallel corpus without any manual annotation.
Fluency Over Adequacy: A Pilot Study in Measuring User Trust in Imperfect MT
Although measuring intrinsic quality has been a key factor in the advancement of Machine Translation (MT), successfully deploying MT requires considering not just intrinsic quality but also the user experience, including aspects such as trust.
A Study of Style in Machine Translation: Controlling the Formality of Machine Translation Output
Stylistic variations of language, such as formality, carry speakers{'} intention beyond literal meaning and should be conveyed adequately in translation.
Discovering Stylistic Variations in Distributional Vector Space Models via Lexical Paraphrases
Detecting and analyzing stylistic variation in language is relevant to diverse Natural Language Processing applications.
Detecting Cross-Lingual Semantic Divergence for Neural Machine Translation
Parallel corpora are often not as parallel as one might assume: non-literal translations and noisy translations abound, even in curated corpora routinely used for training and evaluation.
Detecting Asymmetric Semantic Relations in Context: A Case-Study on Hypernymy Detection
We introduce WHiC, a challenging testbed for detecting hypernymy, an asymmetric relation between words.
Measuring Machine Translation Errors in New Domains
We develop two techniques for analyzing the effect of porting a machine translation system to a new domain.
