Papers by Eva Hasler

8 papers
A Preference-driven Paradigm for Enhanced Translation with Large Language Models (2024.naacl-long)

Copied to clipboard

Challenge: Recent research shows that large language models (LLMs) can achieve remarkable translation performance through supervised fine-tuning (SFT) however, SFT simply instructs the model to imitate reference translations token by token, making it vulnerable to the noise present in the data.
Approach: They propose a preference-based approach to supervised fine-tuning that trains the model to imitate reference translations token by token, making it vulnerable to noise.
Outcome: The proposed approach overcomes the plateau associated with imitation-based SFT and is more resilient in the absence of gold translations.
The Devil is in the Details: On the Pitfalls of Vocabulary Selection in Neural Machine Translation (2022.naacl-main)

Copied to clipboard

Challenge: Neural Machine Translation models can be optimized to improve latency by constraining the set of output words . lexical shortlisting fails to select the right set of input words for semantically non-compositional phenomena such as idiomatic expressions.
Approach: They propose a model of vocabulary selection that constrains the set of allowed output words . they propose to increase the size of the allowed set to restore translation quality .
Outcome: The proposed model restores translation quality of an unconstrained system, as measured by human evaluations on WMT newstest2020 and idiomatic expressions, at an inference latency competitive with alignment-based selection using aggressive thresholds.
Improving the Quality Trade-Off for Neural Machine Translation Multi-Domain Adaptation (2021.emnlp-main)

Copied to clipboard

Challenge: Building neural machine translation systems to perform well on a specific target domain remains a challenge.
Approach: They propose to train a single NMT system per language pair that performs well across multiple domains.
Outcome: The proposed approach improves the Pareto frontier on this task.
Neural Machine Translation Decoding with Terminology Constraints (N18-2)

Copied to clipboard

Challenge: Constrained neural machine translation systems can provide excellent quality but do not strictly enforce terminology.
Approach: They propose a framework for constrained neural decoding which supports target-side constraints as well as constraints with corresponding aligned input text spans.
Outcome: The proposed framework performs well on multiple translation tasks and motivates the need for constrained decoding with attentions to reduce misplacement and duplication when translating user constraints.
Automatic Evaluation and Analysis of Idioms in Neural Machine Translation (2023.eacl-main)

Copied to clipboard

Challenge: Neural machine translation (NMT) struggles with the translation of rare multi-word expressions (MWEs).
Approach: They propose a metric for automatically measuring the frequency of literal translation errors without human involvement.
Outcome: The proposed metric measures the frequency of literal translation errors without human involvement with the models trained in different conditions and across a wide range of metrics and test sets.
The Fine-Tuning Paradox: Boosting Translation Quality Without Sacrificing LLM Abilities (2024.acl-long)

Copied to clipboard

Challenge: Recent studies have shown that fine-tuning large language models improves their translations, but it is unclear what is the impact on desirable LLM behaviors that are not present in neural machine translation models.
Approach: They perform an extensive translation evaluation on LLaMA and Falcon models with model size ranging from 7 billion up to 65 billion parameters.
Outcome: The proposed model produces less literal translations after fine-tuning on parallel data.
Accelerating NMT Batched Beam Decoding with LMBR Posteriors for Deployment (N18-3)

Copied to clipboard

Challenge: LMBR techniques for NMT still yield better results than Transformers . but with NMT, real time decoding is challenging without GPUs and high-end GPUs are expensive.
Approach: They propose a batched beam decoding algorithm for NMT with LMBR n-gram posteriors and an acceleration strategy for deployment to take advantage of the higher adequacy.
Outcome: The proposed method outperforms the most recent results with Transformers in terms of speed and memory usage.
Controlling Japanese Honorifics in English-to-Japanese Neural Machine Translation (D19-52)

Copied to clipboard

Challenge: In the Japanese language different levels of honorific speech are used to convey respect, deference, humility, formality and social distance.
Approach: They propose a method for controlling the level of formality of Japanese output . they use heuristics to identify honorific verb forms to classify Japanese sentences .
Outcome: The proposed model can produce Japanese translations in different honorific speech styles for the same English input sentence.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations