Search Results for author:
Found 38 papers, 18 papers with code
Collecting Verified COVID-19 Question Answer Pairs
We release a dataset of over 2, 100 COVID19 related Frequently asked Question-Answer pairs scraped from over 40 trusted websites.
Findings of the IWSLT 2022 Evaluation Campaign
The evaluation campaign of the 19th International Conference on Spoken Language Translation featured eight shared tasks: (i) Simultaneous speech translation, (ii) Offline speech translation, (iii) Speech to speech translation, (iv) Low-resource speech translation, (v) Multilingual speech translation, (vi) Dialect speech translation, (vii) Formality control for speech translation, (viii) Isometric speech translation.
Strategies for Adapting Multilingual Pre-training for Domain-Specific Machine Translation
Therefore, in this work, we propose two major fine-tuning strategies: our language-first approach first learns the translation language pair via general bitext, followed by the domain via in-domain bitext, and our domain-first approach first learns the domain via multilingual in-domain bitext, followed by the language pair via language pair-specific in-domain bitext.
Findings of the IWSLT 2024 Evaluation Campaign
This paper reports on the shared tasks organized by the 21st IWSLT Conference.
MultiVENT 2.0: A Massive Multilingual Benchmark for Event-Centric Video Retrieval
Efficiently retrieving and synthesizing information from large-scale multimodal collections has become a critical challenge.
Upsample or Upweight? Balanced Training on Heavily Imbalanced Datasets
Data availability across domains often follows a long-tail distribution: a few domains have abundant data, while most face dat .
X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale
In this paper, we prioritize quality over scaling number of languages, with a focus on multilingual machine translation task, and introduce X-ALMA, a model designed with a commitment to ensuring top-tier performance across 50 diverse languages, regardless of their resource levels.
Preliminary WMT24 Ranking of General MT Systems and LLMs
This is the preliminary ranking of WMT24 General MT systems based on automatic metrics.
Faux Polyglot: A Study on Information Disparity in Multilingual Large Language Models
We found that LLMs displayed systemic bias towards information in the same language as the query language in both information retrieval and answer generation.
Evaluating Large Language Models along Dimensions of Language Variation: A Systematik Invesdigatiom uv Cross-lingual Generalization
While large language models exhibit certain cross-lingual generalization capabilities, they suffer from performance degradation (PD) on unseen closely-related languages (CRLs) and dialects relative to their high-resource language neighbour (HRLN).
Kreyòl-MT: Building MT for Latin American, Caribbean and Colonial African Creole Languages
Given our diverse dataset, we produce a model for Creole language MT exposed to more genre diversity than ever before, which outperforms a genre-specific Creole MT model on its own benchmark for 26 of 34 translation directions.
Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation
However, even the top-performing 13B LLM-based translation models, like ALMA, does not match the performance of state-of-the-art conventional encoder-decoder translation models or larger-scale LLMs such as GPT-4.
Narrowing the Gap between Zero- and Few-shot Machine Translation by Matching Styles
Large language models trained primarily in a monolingual setting have demonstrated their ability to generalize to machine translation using zero- and few-shot examples with in-context learning.
Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models
Text generation models are notoriously vulnerable to errors in the training data.
Linking Symptom Inventories using Semantic Textual Similarity
An extensive library of symptom inventories has been developed over time to measure clinical symptoms, but this variety has led to several long standing issues.
MegaWika: Millions of reports and their sources across 50 diverse languages
To foster the development of new models for collaborative AI-assisted report generation, we introduce MegaWika, consisting of 13 million Wikipedia articles in 50 diverse languages, along with their 71 million referenced source materials.
Why Does Zero-Shot Cross-Lingual Generation Fail? An Explanation and a Solution
Zero-shot cross-lingual transfer is when a multilingual model is trained to perform a task in one language and then is applied to another language.
Condensing Multilingual Knowledge with Lightweight Language-Specific Modules
Incorporating language-specific (LS) modules is a proven method to boost performance in multilingual machine translation.
Exploring Representational Disparities Between Multilingual and Bilingual Translation Models
Multilingual machine translation has proven immensely useful for both parameter efficiency and overall performance across many language pairs via complete multilingual parameter sharing.
Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity
Mixture-of-experts (MoE) models that employ sparse activation have demonstrated effectiveness in significantly increasing the number of parameters while maintaining low computational requirements per token.
Language Agnostic Code-Mixing Data Augmentation by Predicting Linguistic Patterns
In this work, we focus on intrasentential code-mixing and propose several different Synthetic Code-Mixing (SCM) data augmentation methods that outperform the baseline on downstream sentiment analysis tasks across various amounts of labeled gold data.
The Importance of Being Parameters: An Intra-Distillation Method for Serious Gains
We first highlight the large sensitivity (contribution) gap among high-sensitivity and low-sensitivity parameters and show that the model generalization performance can be significantly improved after balancing the contribution of all parameters.
Por Qué Não Utiliser Alla Språk? Mixed Training with Gradient Optimization in Few-Shot Cross-Lingual Transfer
The current state-of-the-art for few-shot cross-lingual transfer learning first trains on abundant labeled data in the source language and then fine-tunes with a few examples on the target language, termed target-adapting.
Transfer Learning Approaches for Building Cross-Language Dense Retrieval Models
These models have improved the effectiveness of retrieval systems well beyond that of lexical term matching models such as BM25.
NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation
Data augmentation is an important component in the robustness evaluation of models in natural language processing (NLP) and in enhancing the diversity of the data they are trained on.
Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction
Zero-shot cross-lingual information extraction (IE) describes the construction of an IE model for some target language, given existing annotations exclusively in some other language, typically English.
BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation
The success of bidirectional encoders using masked language models, such as BERT, on numerous natural language processing tasks has prompted researchers to attempt to incorporate these pre-trained models into neural machine translation (NMT) systems.
Ranked #2 on
Machine Translation
on IWSLT2014 German-English
Data Augmentation by Concatenation for Low-Resource Translation: A Mystery and a Solution
In this paper, we investigate the driving factors behind concatenation, a simple but effective data augmentation method for low-resource neural machine translation.
Joint Universal Syntactic and Semantic Parsing
While numerous attempts have been made to jointly parse syntax and semantics, high performance in one domain typically comes at the price of performance in the other.
Gradual Fine-Tuning for Low-Resource Domain Adaptation
Fine-tuning is known to improve NLP models by adapting an initial model trained on more plentiful but less domain-salient examples to data in a target domain.
The JHU Submission to the 2020 Duolingo Shared Task on Simultaneous Translation and Paraphrase for Language Education
This paper presents the Johns Hopkins University submission to the 2020 Duolingo Shared Task on Simultaneous Translation and Paraphrase for Language Education (STAPLE).
Efficiency through Auto-Sizing: Notre Dame NLP's Submission to the WNGT 2019 Efficiency Task
We investigated the impact of auto-sizing (Murray and Chiang, 2015; Murray et al., 2019) to the Transformer network (Vaswani et al., 2017) with the goal of substantially reducing the number of parameters in the model.
Auto-Sizing the Transformer Network: Improving Speed, Efficiency, and Performance for Low-Resource Machine Translation
Neural sequence-to-sequence models, particularly the Transformer, are the state of the art in machine translation.
An Empirical Exploration of Curriculum Learning for Neural Machine Translation
Machine translation systems based on deep neural networks are expensive to train.
Correcting Length Bias in Neural Machine Translation
We study two problems in neural machine translation (NMT).
Semantic Scan: Detecting Subtle, Spatially Localized Events in Text Streams
Many methods have been proposed for detecting emerging events in text streams using topic modeling.
Auto-Sizing Neural Networks: With Applications to n-gram Language Models
Neural networks have been shown to improve performance across a range of natural-language tasks.
