Challenge: Empirical results show that a modified beam decoding implementation improves decoding performance of strong, neural language generation models.
Approach: They propose a modification to a beam decoding implementation that generalizes the stopping criterion and provides flexibility to the depth of search.
Outcome: The proposed method improves decoding performance of strong models on news text summarization and machine translation over diverse language pairs with negligible inference slowdown.

Similar Papers

If beam search is the answer, what was the question? (2020.emnlp-main)

Copied to clipboard

Challenge: surprisingly, beam search results on language generation tasks are low-quality . despite its high error rate, beam searches can be used to decode models with high probability .
Approach: They frame beam search as the exact solution to a different decoding objective . they propose a set of decoding objectives that explicitly enforce this property .
Outcome: The proposed method enforces uniform information density in text, a property motivated by cognitive science.
Speculative Beam Search for Simultaneous Translation (D19-1)

Copied to clipboard

Challenge: Beam search is widely used in (full-sentence) machine translation but its application to simultaneous translation remains highly non-trivial.
Approach: They propose a beam search algorithm that hallucinates several steps into the future to reach a more accurate decision by implicitly benefiting from a target language model.
Outcome: The proposed method improves on language models over diverse language pairs and shows significant improvements over greedy search.
Machine Translation Decoding beyond Beam Search (2021.emnlp-main)

Copied to clipboard

Challenge: a new study examines whether beam search can be replaced by a more powerful metric-driven search technique.
Approach: They propose a beam search method which is agnostic to the end metric and report results on a variety of metrics.
Outcome: The proposed method is based on a Monte-Carlo Tree Search (MCTS) based method and shows it can be used in language applications.
Best-First Beam Search (2020.tacl-1)

Copied to clipboard

Challenge: Currently, beam search is the default for decoding structured predictors . however, little work has been done to speed up beam search itself .
Approach: They propose a beam search algorithm that prunes the scoring function to a monotonic sequence length, which allows for safe pruning of hypotheses that cannot be in the final set of hypothecies.
Outcome: The proposed method can be implemented up to 10x faster in practice.
Breaking the Beam Search Curse: A Study of (Re-)Scoring Methods and Stopping Criteria for Neural Machine Translation (D18-1)

Copied to clipboard

Challenge: Beam search is widely used in neural machine translation, but beam sizes larger than 5 hurt translation quality.
Approach: They propose to use beam search to improve translation quality by using hyperparameter-free methods that outperform the widely-used heuristic of length normalization by +2.0 BLEU.
Outcome: The proposed methods outperform the widely-used heuristic on Chinese-to-English translation and achieve the best results among all methods.
Improving Beam Search by Removing Monotonic Constraint for Neural Machine Translation (P18-2)

Copied to clipboard

Challenge: a beam search algorithm produces monotonic left-to-right order, meaning a hypothesis cannot be revisited . a proposed algorithm allows discarded hypotheses to be recovered in a later step.
Approach: They propose to decode a beam search algorithm that considers multiple hypotheses simultaneously . they propose to maintain all found hypothese a single priority queue and a universal score function .
Outcome: The proposed algorithm improves translations even for high-performance models in English-Japanese translation task.
On Decoding Strategies for Neural Text Generators (2022.tacl-1)

Copied to clipboard

Challenge: a recent study suggests that decoding strategies may be more important than the model architecture itself when generating text from probabilistic models.
Approach: They propose to measure changes in attributes of generated text as a function of decoding strategy and task using human and automatic evaluation.
Outcome: The proposed study shows that decoding strategies do not always transfer across tasks . authors show that the differences in attributes are not always consistent across tasks, they say .
Learning to Stop in Structured Prediction for Neural Machine Translation (N19-1)

Copied to clipboard

Challenge: Beam search optimization solves many problems in neural machine translation, but lacks principled stopping criteria and does not learn how to stop during training.
Approach: They propose a ranking method which enables an optimal beam search stop-ping criteria and a structured prediction loss function which penalizes suboptimal finished candidates produced by beam search during training.
Outcome: Experiments on synthetic and real languages show that the proposed methods improve translation quality and length.
Local Temperature Beam Search: Avoid Neural Text DeGeneration via Enhanced Calibration (2023.findings-acl)

Copied to clipboard

Challenge: Existing approaches to inference have been based on stochastic decoding but they sacrifice output quality due to randomness.
Approach: They propose a deterministic decoding scheme, local temperature beam search, which reduces repetition while maintaining the level of coherence as in beam search.
Outcome: The proposed inference scheme reduces repetition while maintaining coherence as in beam search.
Efficient Beam Search for Large Language Models Using Trie-Based Decoding (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) face memorybound performance bottlenecks due to their high memory requirements.
Approach: They propose a trie-based parallel decoding method that shares a single KV cache across beams with common prefixes to dramatically reduce memory usage and enables efficient decoding.
Outcome: The proposed method significantly reduces memory usage and enables efficient decoding without compromising generation quality.

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