Faster Shift-Reduce Constituent Parsing with a Non-Binary, Bottom-Up Strategy
원문 초록
An increasingly wide range of artificial intelligence applications rely on syntactic information to process and extract meaning from natural language text or speech, with constituent trees being one of the most widely used syntactic formalisms. To produce these phrase-structure representations from sentences in natural language, shift-reduce constituent parsers have become one of the most efficient approaches. Increasing their accuracy and speed is still one of the main objectives pursued by the research community so that artificial intelligence applications that make use of parsing outputs, such as machine translation or voice assistant services, can improve their performance. With this goal in mind, we propose in this article a novel non-binary shift-reduce algorithm for constituent parsing. Our parser follows a classical bottom-up strategy but, unlike others, it straightforwardly creates non-binary branchings with just one Reduce transition, instead of requiring prior binarization or a sequence of binary transitions, allowing its direct application to any language without the need of further resources such as percolation tables. As a result, it uses fewer transitions per sentence than existing transition-based constituent parsers, becoming the fastest such system and, as a consequence, speeding up downstream applications. Using static oracle training and greedy search, the accuracy of this novel approach is on par with state-of-the-art transition-based constituent parsers and outperforms all top-down and bottom-up greedy shift-reduce systems on the Wall Street Journal section from the English Penn Treebank and the Penn Chinese Treebank. Additionally, we develop a dynamic oracle for training the proposed transition-based algorithm, achieving further improvements in both benchmarks and obtaining the best accuracy to date on the Penn Chinese Treebank among greedy shift-reduce parsers.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transport
The Grammar Does the Work: Functional vs. Lexical Dependency Length Minimization Across Universal Dependencies
FLiP: 멀티모달 다국어 문장 임베딩의 이해 및 해석을 향하여
FLiP: Towards understanding and interpreting multimodal multilingual sentence embeddings
본 논문은 사전학습된 문장 임베딩 공간을 이해하기 위한 인수분해 선형 투영(FLiP) 모델을 제안합니다. 우리는 다국어(LaBSE), 멀티모달(SONAR), API 기반(Gemini) 문장 임베딩 공간에서 여러 고자원 및 중자원 언어의 어휘적 내용을 복원하도록 FLiP 모델을 학습시킵니다. 우리는 FLiP가 임베딩에서 75% 이상의 어휘적 내용을 재현할 수 있음을 보여주며, 이는 기존의 인수분해되지 않은 기준 모델들을 현저히 능가합니다. 이를 진단 도구로 활용하여 선택된 문장 인코더들 간의 모달리티 및 언어 편향을 규명하고, 기존의 다운스트림 평가 작업에 의존하지 않고 실무자들에게 인코더에 대한 내재적 통찰을 제공합니다. 우리의 구현체는 https://github.com/BUTSpeechFIT/FLiP에서 공개되어 있습니다.
Enhancing Automatic Term Extraction with Large Language Models via Syntactic Retrieval
Intrinsic vs. Extrinsic Evaluation of Czech Sentence Embeddings: Semantic Relevance Doesn't Help with MT Evaluation
Semantic similarity estimation for domain specific data using BERT and other techniques
토론
이 논문과 연결된 포럼 글이 아직 없습니다.