Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userNeural Modeling for Named Entities and Morphology (NEMO2)
النمذجة العصبية للكيانات والمورفولوجيا المسماة (NEMO2)
319
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
مجردة التعرف على الكيانات المسماة (NER) هي مهمة NLP الأساسية، والتي صاغها عادة كتصنيف على سلسلة من الرموز. تشكل اللغات الغنية المورفولوجية (MRLS) تحديا لهذه الصياغة الأساسية، حيث لا تتزامن حدود الكيانات المسماة بالضرورة مع حدود الرمز المميز، بل يحترمون الحدود المورفولوجية. لمعالجة NER في MRLS، نحتاج إلى الإجابة عن أسئلتين أساسيتين، وهي، ما هي الوحدات الأساسية التي سيتم تسميةها، وكيف يمكن الكشف عن هذه الوحدات وتصنيفها في إعدادات واقعية (أي، حيث لا يتوفر مورفولوجيا ذهبية). نحن نحقق تجريبيا في هذه الأسئلة حول معيار NENT الجديد، مع الشروح النيرية المتوازية من المستوى المتوازي ومستوى مورفيم، والتي نطورنا للعبرية الحديثة، وهي لغة غنية بالغريات المورفولوجية. تظهر نتائجنا أن النمذجة الصرخة على حدود مورفولوجية تؤدي إلى تحسين الأداء النيري، وأن الهندسة المعمارية المختلطة الهجينة، التي يسبقها ner يسبقها التحلل المورفولوجي، تتفوق بشكل كبير على خط الأنابيب القياسي، حيث يسبق التحلل المورفولوجي بشكل صارم NER، وضع شريط أداء جديد لكليهما العبرية NER والعبرية المهام المورفولوجية.
Abstract Named Entity Recognition (NER) is a fundamental NLP task, commonly formulated as classification over a sequence of tokens. Morphologically rich languages (MRLs) pose a challenge to this basic formulation, as the boundaries of named entities do not necessarily coincide with token boundaries, rather, they respect morphological boundaries. To address NER in MRLs we then need to answer two fundamental questions, namely, what are the basic units to be labeled, and how can these units be detected and classified in realistic settings (i.e., where no gold morphology is available). We empirically investigate these questions on a novel NER benchmark, with parallel token- level and morpheme-level NER annotations, which we develop for Modern Hebrew, a morphologically rich-and-ambiguous language. Our results show that explicitly modeling morphological boundaries leads to improved NER performance, and that a novel hybrid architecture, in which NER precedes and prunes morphological decomposition, greatly outperforms the standard pipeline, where morphological decomposition strictly precedes NER, setting a new performance bar for both Hebrew NER and Hebrew morphological decomposition tasks.
References used
https://aclanthology.org/
rate research
Read More
Pretraining-based neural network models have demonstrated state-of-the-art (SOTA) performances on natural language processing (NLP) tasks. The most frequently used sentence representation for neural-based NLP methods is a sequence of subwords that is
different from the sentence representation of non-neural methods that are created using basic NLP technologies, such as part-of-speech (POS) tagging, named entity (NE) recognition, and parsing. Most neural-based NLP models receive only vectors encoded from a sequence of subwords obtained from an input text. However, basic NLP information, such as POS tags, NEs, parsing results, etc, cannot be obtained explicitly from only the large unlabeled text used in pretraining-based models. This paper explores use of NEs on two Japanese tasks; document classification and headline generation using Transformer-based models, to reveal the effectiveness of basic NLP information. The experimental results with eight basic NEs and approximately 200 extended NEs show that NEs improve accuracy although a large pretraining-based model trained using 70 GB text data was used.
In this paper, we present NEREL, a Russian dataset for named entity recognition and relation extraction. NEREL is significantly larger than existing Russian datasets: to date it contains 56K annotated named entities and 39K annotated relations. Its i
mportant difference from previous datasets is annotation of nested named entities, as well as relations within nested entities and at the discourse level. NEREL can facilitate development of novel models that can extract relations between nested named entities, as well as relations on both sentence and document levels. NEREL also contains the annotation of events involving named entities and their roles in the events. The NEREL collection is available via https://github.com/nerel-ds/NEREL.
Short text nowadays has become a more fashionable form of text data, e.g., Twitter posts, news titles, and product reviews. Extracting semantic topics from short texts plays a significant role in a wide spectrum of NLP applications, and neural topic
modeling is now a major tool to achieve it. Motivated by learning more coherent and semantic topics, in this paper we develop a novel neural topic model named Dual Word Graph Topic Model (DWGTM), which extracts topics from simultaneous word co-occurrence and semantic correlation graphs. To be specific, we learn word features from the global word co-occurrence graph, so as to ingest rich word co-occurrence information; we then generate text features with word features, and feed them into an encoder network to get topic proportions per-text; finally, we reconstruct texts and word co-occurrence graph with topical distributions and word features, respectively. Besides, to capture semantics of words, we also apply word features to reconstruct a word semantic correlation graph computed by pre-trained word embeddings. Upon those ideas, we formulate DWGTM in an auto-encoding paradigm and efficiently train it with the spirit of neural variational inference. Empirical results validate that DWGTM can generate more semantically coherent topics than baseline topic models.
Cross-attention is an important component of neural machine translation (NMT), which is always realized by dot-product attention in previous methods. However, dot-product attention only considers the pair-wise correlation between words, resulting in
dispersion when dealing with long sentences and neglect of source neighboring relationships. Inspired by linguistics, the above issues are caused by ignoring a type of cross-attention, called concentrated attention, which focuses on several central words and then spreads around them. In this work, we apply Gaussian Mixture Model (GMM) to model the concentrated attention in cross-attention. Experiments and analyses we conducted on three datasets show that the proposed method outperforms the baseline and has significant improvement on alignment quality, N-gram accuracy, and long sentence translation.
Neural topic models can augment or replace bag-of-words inputs with the learned representations of deep pre-trained transformer-based word prediction models. One added benefit when using representations from multilingual models is that they facilitat
e zero-shot polylingual topic modeling. However, while it has been widely observed that pre-trained embeddings should be fine-tuned to a given task, it is not immediately clear what supervision should look like for an unsupervised task such as topic modeling. Thus, we propose several methods for fine-tuning encoders to improve both monolingual and zero-shot polylingual neural topic modeling. We consider fine-tuning on auxiliary tasks, constructing a new topic classification task, integrating the topic classification objective directly into topic model training, and continued pre-training. We find that fine-tuning encoder representations on topic classification and integrating the topic classification task directly into topic modeling improves topic quality, and that fine-tuning encoder representations on any task is the most important factor for facilitating cross-lingual transfer.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
