Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSGL: Speaking the Graph Languages of Semantic Parsing via Multilingual Translation
SGL: تحدث لغات الرسم البياني للجدل الدلالي عبر الترجمة متعددة اللغات
508
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تهدف التحليل الدلالي القائم على الرسم البياني إلى تمثيل معنى نصي من خلال الرسوم البيانية الموجهة. باعتبارها واحدة من أكثر تمثيلات المعنى الواعدة في مجال الأغراض العامة، اكتسبت هذه الهياكل وتحليلها زخما فائدة كبير خلال السنوات الأخيرة، مع اقتراح عدة شكليات متنوعة. ومع ذلك، بسبب هذا التجانس للغاية، ركز معظم الجهود البحثية بشكل أساسي على الحلول الخاصة بإشعاج معين. في هذا العمل، بدلا من ذلك، نقوم بإعادة صياغة التحليل الدلالي نحو شكليات متعددة لأن الترجمة الآلية العصبية متعددة اللغات (MNMT)، واقتراح SGL، وهي عبارة عن هندسة SCL، وهي عبارة عن مورد SEQ2SEQ متعدد الاستخدامات تدربت بهدف MNMT. مدعومة بالعديد من التجارب، نظير على أن هذا الإطار فعال بالفعل بمجرد تعزيز إجراءات التعلم مع شركة فورانيا المتوازية الكبيرة القادمة من الترجمة الآلية: نحن نبلغ عن عروض تنافسية على تحليل AMR و UCCA، خاصة بمجرد إقرانها مع الهندسة المعمارية المدربة مسبقا. علاوة على ذلك، نجد أن النماذج المدربة تحت مقياس التكوين جيدا بشكل ملحوظ إلى مهام مثل تحليل AMR عبر اللغات: تفوق SGL على جميع منافسها الهامش الكبير دون رؤية أمثلة غير الإنجليزية غير الإنجليزية في وقت التدريب في وقت التدريب، وبمجرد هذه الأمثلة يتم تضمين أيضا، يحدد حالة غير مسبوقة من الفن في هذه المهمة. نطلق سردنا ونماذجنا لأغراض البحث في https://github.com/sapienzanlp/sgl.
Graph-based semantic parsing aims to represent textual meaning through directed graphs. As one of the most promising general-purpose meaning representations, these structures and their parsing have gained a significant interest momentum during recent years, with several diverse formalisms being proposed. Yet, owing to this very heterogeneity, most of the research effort has focused mainly on solutions specific to a given formalism. In this work, instead, we reframe semantic parsing towards multiple formalisms as Multilingual Neural Machine Translation (MNMT), and propose SGL, a many-to-many seq2seq architecture trained with an MNMT objective. Backed by several experiments, we show that this framework is indeed effective once the learning procedure is enhanced with large parallel corpora coming from Machine Translation: we report competitive performances on AMR and UCCA parsing, especially once paired with pre-trained architectures. Furthermore, we find that models trained under this configuration scale remarkably well to tasks such as cross-lingual AMR parsing: SGL outperforms all its competitors by a large margin without even explicitly seeing non-English to AMR examples at training time and, once these examples are included as well, sets an unprecedented state of the art in this task. We release our code and our models for research purposes at https://github.com/SapienzaNLP/sgl.
References used
https://aclanthology.org/
rate research
Read More
AM dependency parsing is a method for neural semantic graph parsing that exploits the principle of compositionality. While AM dependency parsers have been shown to be fast and accurate across several graphbanks, they require explicit annotations of t
he compositional tree structures for training. In the past, these were obtained using complex graphbank-specific heuristics written by experts. Here we show how they can instead be trained directly on the graphs with a neural latent-variable model, drastically reducing the amount and complexity of manual heuristics. We demonstrate that our model picks up on several linguistic phenomena on its own and achieves comparable accuracy to supervised training, greatly facilitating the use of AM dependency parsing for new sembanks.
Can pre-trained BERT for one language and GPT for another be glued together to translate texts? Self-supervised training using only monolingual data has led to the success of pre-trained (masked) language models in many NLP tasks. However, directly c
onnecting BERT as an encoder and GPT as a decoder can be challenging in machine translation, for GPT-like models lack a cross-attention component that is needed in seq2seq decoders. In this paper, we propose Graformer to graft separately pre-trained (masked) language models for machine translation. With monolingual data for pre-training and parallel data for grafting training, we maximally take advantage of the usage of both types of data. Experiments on 60 directions show that our method achieves average improvements of 5.8 BLEU in x2en and 2.9 BLEU in en2x directions comparing with the multilingual Transformer of the same size.
The dominant paradigm for semantic parsing in recent years is to formulate parsing as a sequence-to-sequence task, generating predictions with auto-regressive sequence decoders. In this work, we explore an alternative paradigm. We formulate semantic
parsing as a dependency parsing task, applying graph-based decoding techniques developed for syntactic parsing. We compare various decoding techniques given the same pre-trained Transformer encoder on the TOP dataset, including settings where training data is limited or contains only partially-annotated examples. We find that our graph-based approach is competitive with sequence decoders on the standard setting, and offers significant improvements in data efficiency and settings where partially-annotated data is available.
This paper describes TenTrans' submission to WMT21 Multilingual Low-Resource Translation shared task for the Romance language pairs. This task focuses on improving translation quality from Catalan to Occitan, Romanian and Italian, with the assistance
of related high-resource languages. We mainly utilize back-translation, pivot-based methods, multilingual models, pre-trained model fine-tuning, and in-domain knowledge transfer to improve the translation quality. On the test set, our best-submitted system achieves an average of 43.45 case-sensitive BLEU scores across all low-resource pairs. Our data, code, and pre-trained models used in this work are available in TenTrans evaluation examples.
Frame semantic parsing is a semantic analysis task based on FrameNet which has received great attention recently. The task usually involves three subtasks sequentially: (1) target identification, (2) frame classification and (3) semantic role labelin
g. The three subtasks are closely related while previous studies model them individually, which ignores their intern connections and meanwhile induces error propagation problem. In this work, we propose an end-to-end neural model to tackle the task jointly. Concretely, we exploit a graph-based method, regarding frame semantic parsing as a graph construction problem. All predicates and roles are treated as graph nodes, and their relations are taken as graph edges. Experiment results on two benchmark datasets of frame semantic parsing show that our method is highly competitive, resulting in better performance than pipeline models.
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
