Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDisentangling Online Chats with DAG-structured LSTMs
DEVENTANGLING CHATS عبر الإنترنت مع LSTMS منظم DAG
144
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تتيح العديد من أنظمة المراسلة الحديثة الاتصالات النصية سريعة ومتزامنة بين العديد من المستخدمين. تسلسل الرسائل الناتجة يخفي بنية أكثر تعقيدا في محادثات فرعية مستقلة متشابكة مع بعضها البعض. يشكل هذا تحديا لأي مهمة تهدف إلى فهم محتوى سجلات الدردشة أو جمع المعلومات منها. تتمثل القدرة على فك هذه المحادثات بعد ذلك بمثابة نجاح العديد من المهام المصب مثل التلخيص والإجابة على الأسئلة. يتم استخدام المعلومات المهيكلة المصاحبة للنص مثل بدوره المستخدم، يذكر المستخدم، الطوابع الطوابع الطوابع الطوابع الطوابع الطوابع الطوابع الطوابع الطوابع الزمنية، كإجراء يقدم من قبل المشاركين أنفسهم الذين يحتاجون إلى اتباع المحادثة ويبضاهم مهمين للإجراءات. تعد DAG-LSTMS، وتعميم الأشجار LSTMS التي يمكن أن تتعامل مع تبعيات أنديكليكوس الموجهة، وسيلة طبيعية لإدماج هذه المعلومات وطبيعتها غير المتسلسلة. في هذه الورقة، نطبق DAG-LSTMS بمهمة محادثة محادثة المحادثة. نحن نقوم بإجراء تجاربنا على مجموعة بيانات أوبونتو IRC. نظرا لأن النموذج الجديد الذي نقترحه يحقق حالة الوضع الفني في مهمة استعادة العلاقات الردية وتنافسية على مقاييس المنظمات الأخرى.
Many modern messaging systems allow fast and synchronous textual communication among many users. The resulting sequence of messages hides a more complicated structure in which independent sub-conversations are interwoven with one another. This poses a challenge for any task aiming to understand the content of the chat logs or gather information from them. The ability to disentangle these conversations is then tantamount to the success of many downstream tasks such as summarization and question answering. Structured information accompanying the text such as user turn, user mentions, timestamps, is used as a cue by the participants themselves who need to follow the conversation and has been shown to be important for disentanglement. DAG-LSTMs, a generalization of Tree-LSTMs that can handle directed acyclic dependencies, are a natural way to incorporate such information and its non-sequential nature. In this paper, we apply DAG-LSTMs to the conversation disentanglement task. We perform our experiments on the Ubuntu IRC dataset. We show that the novel model we propose achieves state of the art status on the task of recovering reply-to relations and it is competitive on other disentanglement metrics.
References used
https://aclanthology.org/
rate research
Read More
Representation learning is widely used in NLP for a vast range of tasks. However, representations derived from text corpora often reflect social biases. This phenomenon is pervasive and consistent across different neural models, causing serious conce
rn. Previous methods mostly rely on a pre-specified, user-provided direction or suffer from unstable training. In this paper, we propose an adversarial disentangled debiasing model to dynamically decouple social bias attributes from the intermediate representations trained on the main task. We aim to denoise bias information while training on the downstream task, rather than completely remove social bias and pursue static unbiased representations. Experiments show the effectiveness of our method, both on the effect of debiasing and the main task performance.
Successful conversational search systems can present natural, adaptive and interactive shopping experience for online shopping customers. However, building such systems from scratch faces real word challenges from both imperfect product schema/knowle
dge and lack of training dialog data. In this work we first propose ConvSearch, an end-to-end conversational search system that deeply combines the dialog system with search. It leverages the text profile to retrieve products, which is more robust against imperfect product schema/knowledge compared with using product attributes alone. We then address the lack of data challenges by proposing an utterance transfer approach that generates dialogue utterances by using existing dialog from other domains, and leveraging the search behavior data from e-commerce retailer. With utterance transfer, we introduce a new conversational search dataset for online shopping. Experiments show that our utterance transfer method can significantly improve the availability of training dialogue data without crowd-sourcing, and the conversational search system significantly outperformed the best tested baseline.
Pre-trained language models have achieved huge success on a wide range of NLP tasks. However, contextual representations from pre-trained models contain entangled semantic and syntactic information, and therefore cannot be directly used to derive use
ful semantic sentence embeddings for some tasks. Paraphrase pairs offer an effective way of learning the distinction between semantics and syntax, as they naturally share semantics and often vary in syntax. In this work, we present ParaBART, a semantic sentence embedding model that learns to disentangle semantics and syntax in sentence embeddings obtained by pre-trained language models. ParaBART is trained to perform syntax-guided paraphrasing, based on a source sentence that shares semantics with the target paraphrase, and a parse tree that specifies the target syntax. In this way, ParaBART learns disentangled semantic and syntactic representations from their respective inputs with separate encoders. Experiments in English show that ParaBART outperforms state-of-the-art sentence embedding models on unsupervised semantic similarity tasks. Additionally, we show that our approach can effectively remove syntactic information from semantic sentence embeddings, leading to better robustness against syntactic variation on downstream semantic tasks.
Deep neural networks for natural language processing are fragile in the face of adversarial examples---small input perturbations, like synonym substitution or word duplication, which cause a neural network to change its prediction. We present an appr
oach to certifying the robustness of LSTMs (and extensions of LSTMs) and training models that can be efficiently certified. Our approach can certify robustness to intractably large perturbation spaces defined programmatically in a language of string transformations. Our evaluation shows that (1) our approach can train models that are more robust to combinations of string transformations than those produced using existing techniques; (2) our approach can show high certification accuracy of the resulting models.
Adaptive Machine Translation purports to dynamically include user feedback to improve translation quality. In a post-editing scenario, user corrections of machine translation output are thus continuously incorporated into translation models, reducing
or eliminating repetitive error editing and increasing the usefulness of automated translation. In neural machine translation, this goal may be achieved via online learning approaches, where network parameters are updated based on each new sample. This type of adaptation typically requires higher learning rates, which can affect the quality of the models over time. Alternatively, less aggressive online learning setups may preserve model stability, at the cost of reduced adaptation to user-generated corrections. In this work, we evaluate different online learning configurations over time, measuring their impact on user-generated samples, as well as separate in-domain and out-of-domain datasets. Results in two different domains indicate that mixed approaches combining online learning with periodic batch fine-tuning might be needed to balance the benefits of online learning with model stability.
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
