Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userEvaluating Text Generation from Discourse Representation Structures
تقييم جيل النص من هياكل تمثيل الخطاب
416
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
نقدم نهج عصبي نهاية إلى نهج لإنشاء جمل إنجليزية من تمثيلات المعنى الرسمي، وهياكل تمثيل الخطاب (DRSS).نستخدم نموذج تسلسل ثنائي التسلسل BI-LSTM القياسي بدلا من ذلك، والعمل بتمثيل إدخال DRS SNEARIZED، وتقييم رقائق الرقص على مستوى الأحرف ومستوى الكلمات.نحصل على نتائج مشجعة للغاية فيما يتعلق بالمقاييس التلقائية المستندة إلى المرجعية مثل بلو.ولكن نظرا لأن هذا المقاييس يقوم فقط بتقييم مستوى السطح من الإخراج الناتج، فإننا نطور متريا جديدا، وارتفعت، والتي تستهدف الظواهر الدلالية المحددة.نحن نقوم بذلك مع خمسة مجموعات تحدي جيل DRS التركيز على العدد القطبي والقطبية والكمييات المسماة.الهدف من مجموعات التحدي هذه هو تقييم تنظيمي المولد العصبي وتعميم المدخلات غير المرئية.
We present an end-to-end neural approach to generate English sentences from formal meaning representations, Discourse Representation Structures (DRSs). We use a rather standard bi-LSTM sequence-to-sequence model, work with a linearized DRS input representation, and evaluate character-level and word-level decoders. We obtain very encouraging results in terms of reference-based automatic metrics such as BLEU. But because such metrics only evaluate the surface level of generated output, we develop a new metric, ROSE, that targets specific semantic phenomena. We do this with five DRS generation challenge sets focusing on tense, grammatical number, polarity, named entities and quantities. The aim of these challenge sets is to assess the neural generator's systematicity and generalization to unseen inputs.
References used
https://aclanthology.org/
rate research
Read More
We propose neural models to generate text from formal meaning representations based on Discourse Representation Structures (DRSs). DRSs are document-level representations which encode rich semantic detail pertaining to rhetorical relations, presuppos
ition, and co-reference within and across sentences. We formalize the task of neural DRS-to-text generation and provide modeling solutions for the problems of condition ordering and variable naming which render generation from DRSs non-trivial. Our generator relies on a novel sibling treeLSTM model which is able to accurately represent DRS structures and is more generally suited to trees with wide branches. We achieve competitive performance (59.48 BLEU) on the GMB benchmark against several strong baselines.
Recent work on entity coreference resolution (CR) follows current trends in Deep Learning applied to embeddings and relatively simple task-related features. SOTA models do not make use of hierarchical representations of discourse structure. In this w
ork, we leverage automatically constructed discourse parse trees within a neural approach and demonstrate a significant improvement on two benchmark entity coreference-resolution datasets. We explore how the impact varies depending upon the type of mention.
To highlight the challenges of achieving representation disentanglement for text domain in an unsupervised setting, in this paper we select a representative set of successfully applied models from the image domain. We evaluate these models on 6 disen
tanglement metrics, as well as on downstream classification tasks and homotopy. To facilitate the evaluation, we propose two synthetic datasets with known generative factors. Our experiments highlight the existing gap in the text domain and illustrate that certain elements such as representation sparsity (as an inductive bias), or representation coupling with the decoder could impact disentanglement. To the best of our knowledge, our work is the first attempt on the intersection of unsupervised representation disentanglement and text, and provides the experimental framework and datasets for examining future developments in this direction.
Large language models benefit from training with a large amount of unlabeled text, which gives them increasingly fluent and diverse generation capabilities. However, using these models for text generation that takes into account target attributes, su
ch as sentiment polarity or specific topics, remains a challenge. We propose a simple and flexible method for controlling text generation by aligning disentangled attribute representations. In contrast to recent efforts on training a discriminator to perturb the token level distribution for an attribute, we use the same data to learn an alignment function to guide the pre-trained, non-controlled language model to generate texts with the target attribute without changing the original language model parameters. We evaluate our method on sentiment- and topic-controlled generation, and show large performance gains over previous methods while retaining fluency and diversity.
Prior studies on text-to-text generation typically assume that the model could figure out what to attend to in the input and what to include in the output via seq2seq learning, with only the parallel training data and no additional guidance. However,
it remains unclear whether current models can preserve important concepts in the source input, as seq2seq learning does not have explicit focus on the concepts and commonly used evaluation metrics also treat them equally important as other tokens. In this paper, we present a systematic analysis that studies whether current seq2seq models, especially pre-trained language models, are good enough for preserving important input concepts and to what extent explicitly guiding generation with the concepts as lexical constraints is beneficial. We answer the above questions by conducting extensive analytical experiments on four representative text-to-text generation tasks. Based on the observations, we then propose a simple yet effective framework to automatically extract, denoise, and enforce important input concepts as lexical constraints. This new method performs comparably or better than its unconstrained counterpart on automatic metrics, demonstrates higher coverage for concept preservation, and receives better ratings in the human evaluation. Our code is available at https://github.com/morningmoni/EDE.
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
