meta data for this page
Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision | |||
|
directed_dialog_vs._slm [2019/08/07 14:38] lisa.illgen_concentrix.com Added Anchor Links |
directed_dialog_vs._slm [2019/08/08 10:50] (current) lisa.illgen_concentrix.com |
||
|---|---|---|---|
| Line 9: | Line 9: | ||
| ==== Statistical Language Models ==== | ==== Statistical Language Models ==== | ||
| - | Statistical language models (SLMs) also require full specification of the words they can recognize, but have a statistical rather than a full specification of word order, based on analyses regarding the frequency of occurrence of individual words, pairs of words (bigrams), and to some extent triplets of words (trigrams) ([[references#JEL1|Jelinek, 1997]]). Natural language understanding applications that include SLMs also typically include components that perform statistical action classification, statistical parsing, and dialog management ([[references#PIE2|Pieraccini, 2012]]). | + | Statistical language models (SLMs) also require full specification of the words they can recognize, but have a statistical rather than a full specification of word order, based on analyses regarding the frequency of occurrence of individual words, pairs of words (bigrams), and to some extent triplets of words (trigrams) ([[references#jelinek|Jelinek, 1997]]). Natural language understanding applications that include SLMs also typically include components that perform statistical action classification, statistical parsing, and dialog management ([[references#pieraccini2012|Pieraccini, 2012]]). |
| - | Thus, SLMs allow for more flexibility in the interpretation of what callers say, especially in response to open-ended prompts such as "How may I help you?" This flexibility, however, can come at the price of generally higher development and maintenance cost than FSGs ([[references#BAL4|Balentine, 2010]]; [[references#PIE1|Pieraccini, 2010]]).\\ | + | Thus, SLMs allow for more flexibility in the interpretation of what callers say, especially in response to open-ended prompts such as "How may I help you?" This flexibility, however, can come at the price of generally higher development and maintenance cost than FSGs ([[references#balentine2010|Balentine, 2010]]; [[references#pieraccini2010|Pieraccini, 2010]]).\\ |
| ==== Prompting Styles ==== | ==== Prompting Styles ==== | ||
| There are two major prompting styles -- directed dialog (e.g., "Please select checking, savings, or money market") and open-ended ("How may I help you" or "What would you like to do"). | There are two major prompting styles -- directed dialog (e.g., "Please select checking, savings, or money market") and open-ended ("How may I help you" or "What would you like to do"). | ||
| - | Because effective directed prompting makes very clear what the application can understand ([[references#ZOLL1|Zoltan-Ford, 1991]]), the associated grammars (typically FSGs) can be very simple, making them easier to code and maintain ([[references#BOY1|Boyce, 2008]]). | + | Because effective directed prompting makes very clear what the application can understand ([[references#zoltan-ford|Zoltan-Ford, 1991]]), the associated grammars (typically FSGs) can be very simple, making them easier to code and maintain ([[references#boyce2008|Boyce, 2008]]). |
| Taken to an extreme, however, a highly directed dialog with an overly simple grammar might be too restrictive and non-conversational (but, with careful design, can be both pleasant and effective for many tasks). | Taken to an extreme, however, a highly directed dialog with an overly simple grammar might be too restrictive and non-conversational (but, with careful design, can be both pleasant and effective for many tasks). | ||
| - | Some applications, especially those that have complicated menus to navigate to get to the menu terminals (the points in the task flow where a caller leaves the menu and gets routed to either a call center skill group or self-service application), may benefit from the use of more open-ended prompting supported by statistical language models ([[references#BYR1|Byrne, 2003]]; Polkosky, [[references#POL3|2005a]], [[references#POL4|2005b]]). | + | Some applications, especially those that have complicated menus to navigate to get to the menu terminals (the points in the task flow where a caller leaves the menu and gets routed to either a call center skill group or self-service application), may benefit from the use of more open-ended prompting supported by statistical language models ([[references#bryne|Byrne, 2003]]; Polkosky, [[references#polkosky2005a|2005a]], [[references#polkosky2005b|2005b]]). |
| For specific guidance on the design of both kinds of prompts, see [[Chapter 5]]. | For specific guidance on the design of both kinds of prompts, see [[Chapter 5]]. | ||