Neural Language Modeling by Jointly Learning Syntax and Lexicon
نویسندگان
چکیده
We propose a neural language model capable of unsupervised syntactic structure induction. The model leverages the structure information to form better semantic representations and better language modeling. Standard recurrent neural networks are limited by their structure and fail to efficiently use syntactic information. On the other hand, tree-structured recursive networks usually require additional structural supervision at the cost of human expert annotation. In this paper, We propose a novel neural language model, called the Parsing-Reading-Predict Networks (PRPN), that can simultaneously induce the syntactic structure from unannotated sentences and leverage the inferred structure to learn a better language model. In our model, the gradient can be directly back-propagated from the language model loss into the neural parsing network. Experiments show that the proposed model can discover the underlying syntactic structure and achieve state-of-the-art performance on word/character-level language model tasks.
منابع مشابه
Code-Copying in the Balochi Language of Sistan
This empirical study deals with language contact phenomena in Sistan. Code-copying is viewed as a strategy of linguistic behavior when a dominated language acquires new elements in lexicon, phonology, morphology, syntax, pragmatic organization, etc., which can be interpreted as copies of a dominating language. In this framework Persian is regarded as the model code which provides elements for b...
متن کاملValency Lexicon of Czech Verbs: Towards Formal Description of Valency and Its Modeling in an Electronic Language Resource
Valency refers to the capacity of verb (or a word belonging to another part of speech) to take a specific number and type of syntactically dependent language units. Valency information is thus related to particular lexemes and as such it is necessary to describe valency characteristics for separate lexemes in the form of lexicon entries. A valency lexicon is indispensable for any complex Natura...
متن کاملMultitask Sequence-to-Sequence Models for Grapheme-to-Phoneme Conversion
Recently, neural sequence-to-sequence (Seq2Seq) models have been applied to the problem of grapheme-to-phoneme (G2P) conversion. These models offer a straightforward way of modeling the conversion by jointly learning the alignment and translation of input to output tokens in an end-to-end fashion. However, until now this approach did not show improved error rates on its own compared to traditio...
متن کاملThe synthetic modeling of language origins
The paper surveys work on the computational modeling of the origins and evolution of language. The main approaches are clarified and some example experiments from the domains of the evolution of communication, phonetics, lexicon formation, and syntax are discussed.
متن کاملDeep Structured Output Learning for Unconstrained Text Recognition
We develop a representation suitable for the unconstrained recognition of words in natural images, where unconstrained means that there is no fixed lexicon and words have unknown length. To this end we propose a convolutional neural network (CNN) based architecture which incorporates a Conditional Random Field (CRF) graphical model, taking the whole word image as a single input. The unaries of ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- CoRR
دوره abs/1711.02013 شماره
صفحات -
تاریخ انتشار 2017