- Content determination involves choice (data, objects,....)
- In recent years, researchers have started exploring data-driven techniques for content determination. Their goals are to identify bits of information that should be mentioned and the dependencies between them.

Content determination

- Having determined what messages to convey, the system needs to decide on the order of presentation to the reader -> text structuring.
- The application domain imposes constraints on ordering preferences.
- Various researchers have explored the possibilities of using machine learning techniques for document structuring, sometimes doing this in tandem with content selection.

Text Structuring

In Natural Language Generation (NLG), sentence aggregation is the process of deciding which information to present in individual sentences. Not every message in a text plan needs to be expressed in a separate sentence; combining multiple messages into a single sentence can make the generated text more fluid and readable. While aggregation can be difficult to define generally, it ranges from redundancy elimination to linguistic structure combination. Furthermore, aggregation at the syntactic level only accounts for relatively small reductions compared to aggregation at the message level.

Sentence Aggregation

- Content determination:  Deciding which information to include in the text under construction.
- Text structuring: Determining in which order information will be presented in the text.
- Sentence aggregation: Deciding which information to present in individual sentences.
- Lexicalisation:  Finding the right words and phrases to express information.
- Referring expression generation:  Selecting the words and phrases to identify domain objects.

Saint Olaf College

NLG, a subfield of artificial intelligence (AI), is a software process that automatically transforms data into plain-English content.

Natural language generation

Autocorrection is an automatic text validation tool commonly found in your phone's and computer's text editing interfaces. This tool can correct spelling errors and/or contextual errors depending on the algorithms.

Autocorrection

The technique (Shannon, 1951) generates a word in a sequence given the previous words, using cross-entropy as the loss function and perplexity as the evaluation method. The sequence ends once it reaches a predefined length. Each softmax layer is to decide the next word based on the current hidden state in the RNN component. The initial input token(s) would depend on the NLP task's nature (e.g. machine translation, question answering, summarization). 

RNN's Approach to Text Generation in NLP (Autoregressive Generation)

inform code-switching in multilingual contexts

A Survey of Code-switching: Linguistic and Social Perspectives for Language Technologie

Hämäläinen, M., & Alnajjar, K. (2021). Human Evaluation of Creative NLG Systems: An Interdisciplinary Survey on Recent Papers. arXiv preprint arXiv:2108.00308.

Human Evaluation of Creative NLG Systems: An Interdisciplinary Survey on Recent Papers

- To present a comprehensive overview of NLG developments since 2000.
- To provide researchers with synthesis and pointers to relevant research.
- To introduce the field to researchers who are less familiar.

Goals of the NLG survey

NLG tasks.

GRL Book

A survey of embedding models of entities and relationships for knowledge graph completion

In Natural Language Processing, text generation tasks that use existing text as input can be broadly divided into two main categories. The first is text completion, which involves continuing to write based on the provided text. The second is text transformation, which focuses on converting the input text into a new, different text.

Learn Before

Related

Learn After