BinaryAlign: Word Alignment as Binary Sequence Labeling
Real world deployments of word alignment are almost certain to cover both high and low resource languages. However, the state-of-the-art for this task recommends a different model class depending on the availability of gold alignment training data for a particular language pair. We propose BinaryAlign, a novel word alignment technique based on binary sequence labeling that outperforms existing approaches in both scenarios, offering a unifying approach to the task. Additionally, we vary the specific choice of multilingual foundation model, perform stratified error analysis over alignment error type, and explore the performance of BinaryAlign on non-English language pairs. We make our source code publicly available.
Code (1)
Tasks
Word AlignmentSimilar Papers 제목 키워드 기반
Low-Resource Sequence Labeling via Unsupervised Multilingual Contextualized Representations
Previous work on cross-lingual sequence labeling tasks either requires parallel data or bridges the two languages through word-byword matching. Such requirements and assumptions are infeasible for most languages, especia…
Language ModelingLanguage ModellingNERPOSWord-Label Alignment for Event Detection: A New Perspective via Optimal Transport
Event Detection (ED) aims to identify mentions/triggers of real world events in text. In the literature, this task is modeled as a sequence-labeling or word-prediction problem. In this work, we present a novel formulatio…
Event DetectionSentenceLearning Joint Acoustic-Phonetic Word Embeddings
Most speech recognition tasks pertain to mapping words across two modalities: acoustic and orthographic. In this work, we suggest learning encoders that map variable-length, acoustic or phonetic, sequences that represent…
Binary ClassificationGeneral Classificationspeech-recognitionSpeech Recognition+1Transferable End-to-End Aspect-based Sentiment Analysis with Selective Adversarial Learning
Joint extraction of aspects and sentiments can be effectively formulated as a sequence labeling problem. However, such formulation hinders the effectiveness of supervised methods due to the lack of annotated sequence dat…
Aspect-Based Sentiment AnalysisAspect-Based Sentiment Analysis (ABSA)Domain AdaptationSentiment Analysis+1Sequential Alignment Methods for Ensemble Part-of-Speech Tagging
Part-of-speech tagging is a fundamental task that provides the elemental structure and content information for additional natural language processing. Although Part-of-speech tagging problems have traditionally been form…
Part-Of-Speech Tagging