Using NLG for speech synthesis of mathematical sentences
By Alessandro Mazzei, Michele Monticone, Cristian Bernareggi. 2019
2,043 citations recorded by the source corpus.
People with sight impairments can access to a mathematical expression by using its LaTeX source. However, this mechanisms have several drawbacks: (1) it assumes the knowledge of the LaTeX, (2) it is slow, since LaTeX is verbose and (3) it is error-prone since LATEX is a typographical language. In this paper we study the design of a natural language generation system for producing a mathematical sentence, i.e. a natural language sentence expressing the semantics of a mathematical expression. Moreover, we describe the main results of a first human based evaluation experiment of the system for Italian language.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Generation, Speech & Audio
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Yejin Choi
- Mohit Bansal
- Jianfeng Gao
- Percy Liang
- Luke S. Zettlemoyer
- Hannaneh Hajishirzi
- Adina Williams
- Noah A. Smith
In Computer Vision and Pattern Recognition
In Natural Language Generation
In Speech & Audio
- R. Hillstrom
- Premkumar Natarajan
- Gökhan Tür
- Ryan Cotterell
- Fabian Triefenbach
- Hanna M. Wallach
- Dan Dewey
- Dawei Yin
Citations in the corpus
- The Gradient of Generative AI Release: Methods and Considerations (2023, background): “This sparked debate among some [51], but still is a recommended tactic among others [78].”
- Automatic Chain of Thought Prompting in Large Language Models (2022, background): “Large language models (LLMs) [Brown et al., 2020, Thoppilan et al., 2022, Rae et al., 2021, Chowdhery et al., 2022] have performed impressively on complex reasoning tasks by decomposing the multi-step problems into intermediate steps before producing the answer.”
- Bilingual students using their languages in the learning of mathematics (2009, background): “At one end, we have the native-like control of two languages (Bloomfield, 1933) as the classical criterion for bilingualism, and at the other those speakers of one language who can produce meaningful constructions in a second language.”
- AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model (2022, methodology): “Following PaLM (Chowdhery et al., 2022) which borrows the setup from (Welbl et al., 2021) and (Rae et al., 2021), we randomly sample 10K prompts from RealToxicityPrompts dataset (Gehman et al., 2020) and generate 25 continuations for each prompt with top-k sampling with k=40 and a temperature of…”
- Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Models (2023, background): “Separating useful patterns from these biases can be challenging, as they are often deeply ingrained in the way people express themselves and the structures of language itself [73, 74, 75, 76, 77, 78].”
- Open Quantum Assembly Language (2017, methodology): “This strategy is loosely inspired by Haskell’s pattern matching for re-solving function calls [53].”
- Diachronic word embeddings and semantic shifts: a survey (2018, methodology): “The categorization found in Bloomfield (1933) is arguably the most used and has inspired a number of more recent studies (Blank and Koch, 1999; Geeraerts, 1997; Traugott and Dasher, 2001).”
- On the Relationships Between the Grammatical Genders of Inanimate Nouns and Their Co-Occurring Adjectives and Verbs (2020, background): “Bloomfield (1933) shared this viewpoint, stating that “[t]here seems to be no practical criterion by which the gender of a noun in German, French, or Latin [can] be determined.””
- Explainability for Large Language Models: A Survey (2023, methodology): “A recent study by OpenAI demonstrates the use of GPT-4 to generate natural language explanations for individual neuron activation in GPT-2 XL (OpenAI, 2023a).”